diff --git a/docs/resources/inference_deployment.md b/docs/resources/inference_deployment.md index ed46868d9..ea118d9c0 100644 --- a/docs/resources/inference_deployment.md +++ b/docs/resources/inference_deployment.md @@ -60,6 +60,9 @@ In addition to all arguments above, the following attributes are exported: - `private_endpoint` - Private endpoint's attributes. - `id` - (Optional) The id of the private endpoint. - `url` - (Optional) The URL of the endpoint. +- `private_ip` - The private IPv4 address associated with the deployment. + - `id` - The ID of the IPv4 address resource. + - `address` - The private IPv4 address. - `public_endpoint` - (Optional) Public endpoint's attributes. - `id` - (Optional) The id of the public endpoint. - `url` - (Optional) The URL of the endpoint. diff --git a/internal/services/inference/deployment.go b/internal/services/inference/deployment.go index 2413722ed..8d478f2a2 100644 --- a/internal/services/inference/deployment.go +++ b/internal/services/inference/deployment.go @@ -2,17 +2,21 @@ package inference import ( "context" + "fmt" + "github.com/hashicorp/go-cty/cty" "github.com/hashicorp/terraform-plugin-sdk/v2/diag" "github.com/hashicorp/terraform-plugin-sdk/v2/helper/schema" "github.com/hashicorp/terraform-plugin-sdk/v2/helper/validation" "github.com/scaleway/scaleway-sdk-go/api/inference/v1" + ipamAPI "github.com/scaleway/scaleway-sdk-go/api/ipam/v1" "github.com/scaleway/scaleway-sdk-go/scw" "github.com/scaleway/terraform-provider-scaleway/v2/internal/dsf" "github.com/scaleway/terraform-provider-scaleway/v2/internal/httperrors" "github.com/scaleway/terraform-provider-scaleway/v2/internal/locality" "github.com/scaleway/terraform-provider-scaleway/v2/internal/locality/regional" "github.com/scaleway/terraform-provider-scaleway/v2/internal/services/account" + "github.com/scaleway/terraform-provider-scaleway/v2/internal/services/ipam" "github.com/scaleway/terraform-provider-scaleway/v2/internal/types" ) @@ -111,7 +115,6 @@ func ResourceDeployment() *schema.Resource { Computed: true, Description: "The date and time of the last update of the deployment", }, - "private_endpoint": { Type: schema.TypeList, Optional: true, @@ -144,7 +147,6 @@ func ResourceDeployment() *schema.Resource { }, }, }, - "public_endpoint": { Type: schema.TypeList, Optional: true, @@ -177,6 +179,26 @@ func ResourceDeployment() *schema.Resource { }, }, }, + "private_ip": { + Type: schema.TypeList, + Computed: true, + Optional: true, + Description: "The private IPv4 address associated with the deployment", + Elem: &schema.Resource{ + Schema: map[string]*schema.Schema{ + "id": { + Type: schema.TypeString, + Computed: true, + Description: "The ID of the IPv4 address resource", + }, + "address": { + Type: schema.TypeString, + Computed: true, + Description: "The private IPv4 address", + }, + }, + }, + }, }, } } @@ -317,15 +339,64 @@ func ResourceDeploymentRead(ctx context.Context, d *schema.ResourceData, m inter } } + diags := diag.Diagnostics{} + privateIPs := []map[string]interface{}(nil) + authorized := true + if privateEndpoints != nil { _ = d.Set("private_endpoint", privateEndpoints) + + for _, endpoint := range deployment.Endpoints { + if endpoint.PrivateNetwork == nil { + continue + } + + resourceType := ipamAPI.ResourceTypeLlmDeployment + opts := &ipam.GetResourcePrivateIPsOptions{ + ResourceID: &deployment.ID, + ResourceType: &resourceType, + PrivateNetworkID: &endpoint.PrivateNetwork.PrivateNetworkID, + ProjectID: &deployment.ProjectID, + } + + endpointPrivateIPs, err := ipam.GetResourcePrivateIPs(ctx, m, region, opts) + + switch { + case err == nil: + privateIPs = append(privateIPs, endpointPrivateIPs...) + case httperrors.Is403(err): + authorized = false + + diags = append(diags, diag.Diagnostic{ + Severity: diag.Warning, + Summary: "Unauthorized to read deployment's private IP, please check your IAM permissions", + Detail: err.Error(), + AttributePath: cty.GetAttrPath("private_ip"), + }) + default: + diags = append(diags, diag.Diagnostic{ + Severity: diag.Warning, + Summary: fmt.Sprintf("Unable to get private IP for deployment %q", deployment.Name), + Detail: err.Error(), + AttributePath: cty.GetAttrPath("private_ip"), + }) + } + + if !authorized { + break + } + } + } + + if authorized { + _ = d.Set("private_ip", privateIPs) } if publicEndpoints != nil { _ = d.Set("public_endpoint", publicEndpoints) } - return nil + return diags } func ResourceDeploymentUpdate(ctx context.Context, d *schema.ResourceData, m interface{}) diag.Diagnostics { diff --git a/internal/services/inference/deployment_test.go b/internal/services/inference/deployment_test.go index 00aba49ba..c5cb99f4c 100644 --- a/internal/services/inference/deployment_test.go +++ b/internal/services/inference/deployment_test.go @@ -86,6 +86,8 @@ func TestAccDeployment_Endpoint(t *testing.T) { resource.TestCheckResourceAttr("scaleway_inference_deployment.main", "name", "test-inference-deployment-endpoint-private"), resource.TestCheckResourceAttr("scaleway_inference_deployment.main", "node_type", "L4"), resource.TestCheckResourceAttrPair("scaleway_inference_deployment.main", "private_endpoint.0.private_network_id", "scaleway_vpc_private_network.pn01", "id"), + resource.TestCheckResourceAttrSet("scaleway_inference_deployment.main", "private_ip.0.id"), + resource.TestCheckResourceAttrSet("scaleway_inference_deployment.main", "private_ip.0.address"), ), }, { @@ -116,6 +118,8 @@ func TestAccDeployment_Endpoint(t *testing.T) { resource.TestCheckResourceAttr("scaleway_inference_deployment.main", "name", "test-inference-deployment-basic-endpoints-private-public"), resource.TestCheckResourceAttr("scaleway_inference_deployment.main", "public_endpoint.0.is_enabled", "true"), resource.TestCheckResourceAttrPair("scaleway_inference_deployment.main", "private_endpoint.0.private_network_id", "scaleway_vpc_private_network.pn01", "id"), + resource.TestCheckResourceAttrSet("scaleway_inference_deployment.main", "private_ip.0.id"), + resource.TestCheckResourceAttrSet("scaleway_inference_deployment.main", "private_ip.0.address"), ), }, }, diff --git a/internal/services/inference/testdata/deployment-endpoint.cassette.yaml b/internal/services/inference/testdata/deployment-endpoint.cassette.yaml index 17f8002dd..2a49b46d9 100644 --- a/internal/services/inference/testdata/deployment-endpoint.cassette.yaml +++ b/internal/services/inference/testdata/deployment-endpoint.cassette.yaml @@ -16,7 +16,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models?order_by=display_rank_asc&page_size=1000 method: GET response: @@ -25,20 +25,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 50297 + content_length: 50533 uncompressed: false - body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-04-28T18:48:01.860457Z","description":"","has_eula":false,"id":"a19296a6-4cef-447a-99bc-8f6c3ee30df4","name":"TestAccCustomModel_Basic","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-04-30T13:29:24.004776Z","description":"","has_eula":false,"id":"eabb7f74-24a1-4173-911b-26924c1be619","name":"TestAccCustomModel_DeployModelOnServer","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":56960,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:48.796286Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:35.683881Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-07T10:19:23.153808Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' + body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:14.861650Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-21T16:26:14.792208Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-05-21T16:23:31.620336Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"e7599d92-c1d4-4729-9843-63ca2d5f690d","name":"mistral/devstral-small-2505:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":94000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:23:43.338045Z"},{"created_at":"2025-05-21T16:24:34.777647Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"16c82320-33a4-4b75-a69d-172f0744d759","name":"mistral/devstral-small-2505:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:24:45.303772Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:38.997736Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' headers: Content-Length: - - "50297" + - "50533" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:36:48 GMT + - Tue, 27 May 2025 09:56:49 GMT Server: - - Scaleway API Gateway (fr-par-1;edge03) + - Scaleway API Gateway (fr-par-1;edge02) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -46,10 +46,10 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 7913357e-5f2f-4d5c-8365-7b9a1e972f29 + - dd0216ff-36eb-4d01-9905-d3b171ca8bce status: 200 OK code: 200 - duration: 252.033333ms + duration: 451.505458ms - id: 1 request: proto: HTTP/1.1 @@ -65,7 +65,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models/7205dbce-cc80-4b2a-bb7f-3fd3a804afc3 method: GET response: @@ -85,9 +85,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:36:48 GMT + - Tue, 27 May 2025 09:56:49 GMT Server: - - Scaleway API Gateway (fr-par-1;edge03) + - Scaleway API Gateway (fr-par-1;edge02) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -95,10 +95,10 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 3d41f6d5-cf3c-4f9c-a7c7-308268358524 + - 3553527e-be4f-47d1-b2de-bbe9ba33de9b status: 200 OK code: 200 - duration: 39.664417ms + duration: 145.688666ms - id: 2 request: proto: HTTP/1.1 @@ -114,7 +114,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models?order_by=display_rank_asc&page_size=1000 method: GET response: @@ -123,20 +123,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 50297 + content_length: 50533 uncompressed: false - body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-04-28T18:48:01.860457Z","description":"","has_eula":false,"id":"a19296a6-4cef-447a-99bc-8f6c3ee30df4","name":"TestAccCustomModel_Basic","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-04-30T13:29:24.004776Z","description":"","has_eula":false,"id":"eabb7f74-24a1-4173-911b-26924c1be619","name":"TestAccCustomModel_DeployModelOnServer","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":56960,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:48.796286Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:35.683881Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-07T10:19:23.153808Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' + body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:14.861650Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-21T16:26:14.792208Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-05-21T16:23:31.620336Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"e7599d92-c1d4-4729-9843-63ca2d5f690d","name":"mistral/devstral-small-2505:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":94000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:23:43.338045Z"},{"created_at":"2025-05-21T16:24:34.777647Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"16c82320-33a4-4b75-a69d-172f0744d759","name":"mistral/devstral-small-2505:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:24:45.303772Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:38.997736Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' headers: Content-Length: - - "50297" + - "50533" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:36:48 GMT + - Tue, 27 May 2025 09:56:49 GMT Server: - - Scaleway API Gateway (fr-par-1;edge03) + - Scaleway API Gateway (fr-par-1;edge02) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -144,10 +144,10 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 4870582c-8d51-462a-976f-c2c6541e8a8f + - e1023f2b-8758-4263-9173-4dde7499beaf status: 200 OK code: 200 - duration: 229.922375ms + duration: 319.357125ms - id: 3 request: proto: HTTP/1.1 @@ -163,7 +163,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models/7205dbce-cc80-4b2a-bb7f-3fd3a804afc3 method: GET response: @@ -183,9 +183,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:36:48 GMT + - Tue, 27 May 2025 09:56:49 GMT Server: - - Scaleway API Gateway (fr-par-1;edge03) + - Scaleway API Gateway (fr-par-1;edge02) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -193,10 +193,10 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 0e228506-fbff-4b2a-8ea6-bb3dcdf4e682 + - fb696baf-a17f-46c8-b5fa-9c0c4f3d3ffe status: 200 OK code: 200 - duration: 33.941458ms + duration: 36.450125ms - id: 4 request: proto: HTTP/1.1 @@ -208,13 +208,13 @@ interactions: host: api.scaleway.com remote_addr: "" request_uri: "" - body: '{"name":"private-network-test-inference","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","tags":[],"subnets":null}' + body: '{"name":"private-network-test-inference","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","tags":[],"subnets":null}' form: {} headers: Content-Type: - application/json User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/vpc/v2/regions/fr-par/private-networks method: POST response: @@ -223,20 +223,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 1057 + content_length: 1100 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:49.519324Z","dhcp_enabled":true,"id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","name":"private-network-test-inference","organization_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","subnets":[{"created_at":"2025-05-15T09:36:49.519324Z","id":"7633077d-66da-4644-bc1b-dbdf8bca995b","private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","subnet":"172.16.68.0/22","updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"},{"created_at":"2025-05-15T09:36:49.519324Z","id":"7488b8ca-80eb-42b4-aad5-a17471547dfa","private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","subnet":"fd64:badd:7710:82eb::/64","updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"}],"tags":[],"updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"}' + body: '{"created_at":"2025-05-27T09:56:50.279358Z","default_route_propagation_enabled":false,"dhcp_enabled":true,"id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","name":"private-network-test-inference","organization_id":"105bdce1-64c0-48ab-899d-868455867ecf","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","region":"fr-par","subnets":[{"created_at":"2025-05-27T09:56:50.279358Z","id":"b0c59263-2972-4d4f-9904-288650c027a4","private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","subnet":"172.16.16.0/22","updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"},{"created_at":"2025-05-27T09:56:50.279358Z","id":"72aa23a9-066b-4831-9e72-8234f5c5a948","private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","subnet":"fd5f:519c:6d46:2728::/64","updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"}],"tags":[],"updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"}' headers: Content-Length: - - "1057" + - "1100" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:36:50 GMT + - Tue, 27 May 2025 09:56:50 GMT Server: - - Scaleway API Gateway (fr-par-1;edge03) + - Scaleway API Gateway (fr-par-1;edge02) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -244,10 +244,10 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 1c97940e-4b11-432a-9bf7-5b400527a0fa + - 781a84c4-fcc0-4f1d-9394-484765beba78 status: 200 OK code: 200 - duration: 530.426167ms + duration: 616.685792ms - id: 5 request: proto: HTTP/1.1 @@ -263,8 +263,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/vpc/v2/regions/fr-par/private-networks/552f5c0d-40f0-4d67-bb57-727c50641ba9 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/vpc/v2/regions/fr-par/private-networks/a7baa1aa-c738-4871-b9c6-c1b069c59d24 method: GET response: proto: HTTP/2.0 @@ -272,20 +272,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 1057 + content_length: 1100 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:49.519324Z","dhcp_enabled":true,"id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","name":"private-network-test-inference","organization_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","subnets":[{"created_at":"2025-05-15T09:36:49.519324Z","id":"7633077d-66da-4644-bc1b-dbdf8bca995b","private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","subnet":"172.16.68.0/22","updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"},{"created_at":"2025-05-15T09:36:49.519324Z","id":"7488b8ca-80eb-42b4-aad5-a17471547dfa","private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","subnet":"fd64:badd:7710:82eb::/64","updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"}],"tags":[],"updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"}' + body: '{"created_at":"2025-05-27T09:56:50.279358Z","default_route_propagation_enabled":false,"dhcp_enabled":true,"id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","name":"private-network-test-inference","organization_id":"105bdce1-64c0-48ab-899d-868455867ecf","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","region":"fr-par","subnets":[{"created_at":"2025-05-27T09:56:50.279358Z","id":"b0c59263-2972-4d4f-9904-288650c027a4","private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","subnet":"172.16.16.0/22","updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"},{"created_at":"2025-05-27T09:56:50.279358Z","id":"72aa23a9-066b-4831-9e72-8234f5c5a948","private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","subnet":"fd5f:519c:6d46:2728::/64","updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"}],"tags":[],"updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"}' headers: Content-Length: - - "1057" + - "1100" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:36:50 GMT + - Tue, 27 May 2025 09:56:50 GMT Server: - - Scaleway API Gateway (fr-par-1;edge03) + - Scaleway API Gateway (fr-par-1;edge02) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -293,10 +293,10 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 039084c3-1504-465e-9505-958c04766479 + - dd7dbd60-1003-48be-981a-190e6a6afb53 status: 200 OK code: 200 - duration: 27.667125ms + duration: 114.165584ms - id: 6 request: proto: HTTP/1.1 @@ -308,13 +308,13 @@ interactions: host: api.scaleway.com remote_addr: "" request_uri: "" - body: '{"name":"test-inference-deployment-endpoint-private","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","accept_eula":true,"node_type_name":"L4","tags":[],"min_size":1,"max_size":1,"endpoints":[{"private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"disable_auth":false}]}' + body: '{"name":"test-inference-deployment-endpoint-private","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","accept_eula":true,"node_type_name":"L4","tags":[],"min_size":1,"max_size":1,"endpoints":[{"private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"disable_auth":false}]}' form: {} headers: Content-Type: - application/json User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments method: POST response: @@ -325,7 +325,7 @@ interactions: trailer: {} content_length: 717 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":0,"status":"creating","tags":[],"updated_at":null}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":0,"status":"creating","tags":[],"updated_at":null}' headers: Content-Length: - "717" @@ -334,9 +334,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:36:50 GMT + - Tue, 27 May 2025 09:56:51 GMT Server: - - Scaleway API Gateway (fr-par-1;edge03) + - Scaleway API Gateway (fr-par-1;edge02) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -344,10 +344,10 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 7840d252-704a-493b-88a3-c09baedbaee2 + - ddc17274-bcdf-4d26-b88f-c857c5a47f69 status: 200 OK code: 200 - duration: 291.656291ms + duration: 491.071875ms - id: 7 request: proto: HTTP/1.1 @@ -363,8 +363,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -374,7 +374,7 @@ interactions: trailer: {} content_length: 717 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":0,"status":"creating","tags":[],"updated_at":null}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":0,"status":"creating","tags":[],"updated_at":null}' headers: Content-Length: - "717" @@ -383,9 +383,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:36:50 GMT + - Tue, 27 May 2025 09:56:51 GMT Server: - - Scaleway API Gateway (fr-par-1;edge03) + - Scaleway API Gateway (fr-par-1;edge02) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -393,10 +393,10 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - e4119343-7606-4236-bc61-2fdceb6a8618 + - 355b8da1-741a-4454-879c-a83717ab107f status: 200 OK code: 200 - duration: 51.23975ms + duration: 122.375041ms - id: 8 request: proto: HTTP/1.1 @@ -412,8 +412,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -423,7 +423,7 @@ interactions: trailer: {} content_length: 717 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":0,"status":"creating","tags":[],"updated_at":null}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":0,"status":"creating","tags":[],"updated_at":null}' headers: Content-Length: - "717" @@ -432,9 +432,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:37:50 GMT + - Tue, 27 May 2025 09:57:51 GMT Server: - - Scaleway API Gateway (fr-par-1;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -442,10 +442,10 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - e4fe59f1-e3d0-454e-a8c3-121a75d2e742 + - 84b7d19d-5d53-45cf-baca-3aae6310d6e9 status: 200 OK code: 200 - duration: 117.681541ms + duration: 157.039584ms - id: 9 request: proto: HTTP/1.1 @@ -461,8 +461,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -472,7 +472,7 @@ interactions: trailer: {} content_length: 717 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":0,"status":"creating","tags":[],"updated_at":null}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":0,"status":"creating","tags":[],"updated_at":null}' headers: Content-Length: - "717" @@ -481,9 +481,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:38:50 GMT + - Tue, 27 May 2025 09:58:51 GMT Server: - - Scaleway API Gateway (fr-par-3;edge02) + - Scaleway API Gateway (fr-par-1;edge03) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -491,10 +491,10 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 653b13f6-5d50-4955-a26e-0e8738ff7b07 + - 82974489-0f74-4852-8f37-4c64a14963e5 status: 200 OK code: 200 - duration: 95.343917ms + duration: 163.623667ms - id: 10 request: proto: HTTP/1.1 @@ -510,8 +510,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -519,20 +519,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 763 + content_length: 717 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":0,"status":"deploying","tags":[],"updated_at":"2025-05-15T09:39:43.360182Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":0,"status":"creating","tags":[],"updated_at":null}' headers: Content-Length: - - "763" + - "717" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:42:00 GMT + - Tue, 27 May 2025 09:59:52 GMT Server: - - Scaleway API Gateway (fr-par-2;edge03) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -540,10 +540,10 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - a261ad7f-5712-4701-a6f9-b626baac58a9 + - ff83d13f-7353-4d88-bd25-70f5f0c56fb5 status: 200 OK code: 200 - duration: 105.144167ms + duration: 177.740167ms - id: 11 request: proto: HTTP/1.1 @@ -559,8 +559,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -570,7 +570,7 @@ interactions: trailer: {} content_length: 763 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":0,"status":"deploying","tags":[],"updated_at":"2025-05-15T09:39:43.360182Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":0,"status":"deploying","tags":[],"updated_at":"2025-05-27T10:00:09.111358Z"}' headers: Content-Length: - "763" @@ -579,9 +579,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:43:00 GMT + - Tue, 27 May 2025 10:00:52 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge03) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -589,10 +589,10 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 495f22b6-7a1b-47fd-8b40-dea54e3d4c48 + - d78085a3-1710-450b-8e8c-14f989d46882 status: 200 OK code: 200 - duration: 224.630958ms + duration: 168.470708ms - id: 12 request: proto: HTTP/1.1 @@ -608,8 +608,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -619,7 +619,7 @@ interactions: trailer: {} content_length: 763 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":0,"status":"deploying","tags":[],"updated_at":"2025-05-15T09:39:43.360182Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":0,"status":"deploying","tags":[],"updated_at":"2025-05-27T10:00:09.111358Z"}' headers: Content-Length: - "763" @@ -628,9 +628,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:44:00 GMT + - Tue, 27 May 2025 10:01:52 GMT Server: - - Scaleway API Gateway (fr-par-2;edge03) + - Scaleway API Gateway (fr-par-1;edge03) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -638,10 +638,10 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - a642a607-9ba7-4a1e-b2e6-ea01f56eb373 + - bd09eb15-0919-4d13-a589-a3d6c23471f5 status: 200 OK code: 200 - duration: 95.987ms + duration: 158.479833ms - id: 13 request: proto: HTTP/1.1 @@ -657,8 +657,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -668,7 +668,7 @@ interactions: trailer: {} content_length: 763 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":0,"status":"deploying","tags":[],"updated_at":"2025-05-15T09:39:43.360182Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":0,"status":"deploying","tags":[],"updated_at":"2025-05-27T10:00:09.111358Z"}' headers: Content-Length: - "763" @@ -677,9 +677,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:45:00 GMT + - Tue, 27 May 2025 10:02:52 GMT Server: - - Scaleway API Gateway (fr-par-2;edge01) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -687,10 +687,10 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - f4f332ff-79b9-4bde-8ebe-96e9ede956d4 + - 210dac8b-8b44-4ddd-a361-3d446ada4f3b status: 200 OK code: 200 - duration: 91.154ms + duration: 189.627709ms - id: 14 request: proto: HTTP/1.1 @@ -706,8 +706,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -717,7 +717,7 @@ interactions: trailer: {} content_length: 763 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":0,"status":"deploying","tags":[],"updated_at":"2025-05-15T09:39:43.360182Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":0,"status":"deploying","tags":[],"updated_at":"2025-05-27T10:00:09.111358Z"}' headers: Content-Length: - "763" @@ -726,9 +726,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:46:00 GMT + - Tue, 27 May 2025 10:03:52 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge03) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -736,10 +736,10 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 90f2a5f1-b573-4ea7-88fd-89a79f88d87c + - e1fff22d-0eec-40ec-923e-be3fc50f838c status: 200 OK code: 200 - duration: 94.418625ms + duration: 202.256ms - id: 15 request: proto: HTTP/1.1 @@ -755,8 +755,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -766,7 +766,7 @@ interactions: trailer: {} content_length: 763 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":0,"status":"deploying","tags":[],"updated_at":"2025-05-15T09:39:43.360182Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":0,"status":"deploying","tags":[],"updated_at":"2025-05-27T10:00:09.111358Z"}' headers: Content-Length: - "763" @@ -775,9 +775,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:47:00 GMT + - Tue, 27 May 2025 10:04:52 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge03) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -785,10 +785,10 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 301c8668-15a9-4a81-abda-5afaa1eac870 + - 5ae3368b-c35e-4611-a993-8355177951fd status: 200 OK code: 200 - duration: 83.121958ms + duration: 167.020625ms - id: 16 request: proto: HTTP/1.1 @@ -804,8 +804,155 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 + method: GET + response: + proto: HTTP/2.0 + proto_major: 2 + proto_minor: 0 + transfer_encoding: [] + trailer: {} + content_length: 763 + uncompressed: false + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":0,"status":"deploying","tags":[],"updated_at":"2025-05-27T10:00:09.111358Z"}' + headers: + Content-Length: + - "763" + Content-Security-Policy: + - default-src 'none'; frame-ancestors 'none' + Content-Type: + - application/json + Date: + - Tue, 27 May 2025 10:05:53 GMT + Server: + - Scaleway API Gateway (fr-par-1;edge03) + Strict-Transport-Security: + - max-age=63072000 + X-Content-Type-Options: + - nosniff + X-Frame-Options: + - DENY + X-Request-Id: + - 56552fd7-3f73-43aa-9035-07f613b23ef7 + status: 200 OK + code: 200 + duration: 177.804292ms + - id: 17 + request: + proto: HTTP/1.1 + proto_major: 1 + proto_minor: 1 + content_length: 0 + transfer_encoding: [] + trailer: {} + host: api.scaleway.com + remote_addr: "" + request_uri: "" + body: "" + form: {} + headers: + User-Agent: + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 + method: GET + response: + proto: HTTP/2.0 + proto_major: 2 + proto_minor: 0 + transfer_encoding: [] + trailer: {} + content_length: 763 + uncompressed: false + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":0,"status":"deploying","tags":[],"updated_at":"2025-05-27T10:00:09.111358Z"}' + headers: + Content-Length: + - "763" + Content-Security-Policy: + - default-src 'none'; frame-ancestors 'none' + Content-Type: + - application/json + Date: + - Tue, 27 May 2025 10:06:53 GMT + Server: + - Scaleway API Gateway (fr-par-1;edge02) + Strict-Transport-Security: + - max-age=63072000 + X-Content-Type-Options: + - nosniff + X-Frame-Options: + - DENY + X-Request-Id: + - df18a93a-c6fd-4a44-87e2-a870313ee041 + status: 200 OK + code: 200 + duration: 165.498708ms + - id: 18 + request: + proto: HTTP/1.1 + proto_major: 1 + proto_minor: 1 + content_length: 0 + transfer_encoding: [] + trailer: {} + host: api.scaleway.com + remote_addr: "" + request_uri: "" + body: "" + form: {} + headers: + User-Agent: + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 + method: GET + response: + proto: HTTP/2.0 + proto_major: 2 + proto_minor: 0 + transfer_encoding: [] + trailer: {} + content_length: 763 + uncompressed: false + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":0,"status":"deploying","tags":[],"updated_at":"2025-05-27T10:00:09.111358Z"}' + headers: + Content-Length: + - "763" + Content-Security-Policy: + - default-src 'none'; frame-ancestors 'none' + Content-Type: + - application/json + Date: + - Tue, 27 May 2025 10:07:53 GMT + Server: + - Scaleway API Gateway (fr-par-1;edge01) + Strict-Transport-Security: + - max-age=63072000 + X-Content-Type-Options: + - nosniff + X-Frame-Options: + - DENY + X-Request-Id: + - ec4b51dd-a588-472a-8e10-1c49ef1eca08 + status: 200 OK + code: 200 + duration: 663.992209ms + - id: 19 + request: + proto: HTTP/1.1 + proto_major: 1 + proto_minor: 1 + content_length: 0 + transfer_encoding: [] + trailer: {} + host: api.scaleway.com + remote_addr: "" + request_uri: "" + body: "" + form: {} + headers: + User-Agent: + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -815,7 +962,7 @@ interactions: trailer: {} content_length: 759 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-15T09:47:45.790408Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-27T10:08:07.112362Z"}' headers: Content-Length: - "759" @@ -824,9 +971,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:01 GMT + - Tue, 27 May 2025 10:08:54 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -834,11 +981,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 8552fb36-97af-4650-a68c-a3cf8809973c + - f8f51695-d64c-47e9-acab-c858f1014838 status: 200 OK code: 200 - duration: 99.45975ms - - id: 17 + duration: 187.389042ms + - id: 20 request: proto: HTTP/1.1 proto_major: 1 @@ -853,8 +1000,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -864,7 +1011,7 @@ interactions: trailer: {} content_length: 759 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-15T09:47:45.790408Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-27T10:08:07.112362Z"}' headers: Content-Length: - "759" @@ -873,9 +1020,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:01 GMT + - Tue, 27 May 2025 10:08:54 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -883,11 +1030,60 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - b9d88f3a-e0de-4864-a807-3ad261760376 + - 5fce75b4-d054-48fe-85bc-9b29ebfa3370 status: 200 OK code: 200 - duration: 54.053667ms - - id: 18 + duration: 145.258916ms + - id: 21 + request: + proto: HTTP/1.1 + proto_major: 1 + proto_minor: 1 + content_length: 0 + transfer_encoding: [] + trailer: {} + host: api.scaleway.com + remote_addr: "" + request_uri: "" + body: "" + form: {} + headers: + User-Agent: + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/ipam/v1/regions/fr-par/ips?order_by=created_at_desc&private_network_id=a7baa1aa-c738-4871-b9c6-c1b069c59d24&project_id=105bdce1-64c0-48ab-899d-868455867ecf&resource_id=57907164-e1b1-4617-8546-8c950f35e2d9&resource_type=llm_deployment + method: GET + response: + proto: HTTP/2.0 + proto_major: 2 + proto_minor: 0 + transfer_encoding: [] + trailer: {} + content_length: 550 + uncompressed: false + body: '{"ips":[{"address":"172.16.16.2/22","created_at":"2025-05-27T09:56:52.525469Z","id":"aebd6ce8-47a7-40c3-b765-050225bccbcb","is_ipv6":false,"project_id":"105bdce1-64c0-48ab-899d-868455867ecf","region":"fr-par","resource":{"id":"57907164-e1b1-4617-8546-8c950f35e2d9","mac_address":"02:00:00:28:DF:AC","name":"test-inference-deployment-endpoint-private","type":"llm_deployment"},"reverses":[],"source":{"subnet_id":"b0c59263-2972-4d4f-9904-288650c027a4"},"tags":[],"updated_at":"2025-05-27T09:59:10.209907Z","zone":null}],"total_count":1}' + headers: + Content-Length: + - "550" + Content-Security-Policy: + - default-src 'none'; frame-ancestors 'none' + Content-Type: + - application/json + Date: + - Tue, 27 May 2025 10:08:54 GMT + Server: + - Scaleway API Gateway (fr-par-1;edge01) + Strict-Transport-Security: + - max-age=63072000 + X-Content-Type-Options: + - nosniff + X-Frame-Options: + - DENY + X-Request-Id: + - 1c063def-2ed2-4519-8ec1-0170b05c155d + status: 200 OK + code: 200 + duration: 122.382083ms + - id: 22 request: proto: HTTP/1.1 proto_major: 1 @@ -902,8 +1098,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -913,7 +1109,7 @@ interactions: trailer: {} content_length: 759 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-15T09:47:45.790408Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-27T10:08:07.112362Z"}' headers: Content-Length: - "759" @@ -922,9 +1118,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:01 GMT + - Tue, 27 May 2025 10:08:54 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -932,11 +1128,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - ba0f6803-80be-498e-8454-73ffb1387b42 + - b714414f-0497-4a3d-af4e-aa343fea3a0a status: 200 OK code: 200 - duration: 48.278958ms - - id: 19 + duration: 131.077916ms + - id: 23 request: proto: HTTP/1.1 proto_major: 1 @@ -951,7 +1147,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models?order_by=display_rank_asc&page_size=1000 method: GET response: @@ -960,20 +1156,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 50297 + content_length: 50533 uncompressed: false - body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-04-28T18:48:01.860457Z","description":"","has_eula":false,"id":"a19296a6-4cef-447a-99bc-8f6c3ee30df4","name":"TestAccCustomModel_Basic","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-04-30T13:29:24.004776Z","description":"","has_eula":false,"id":"eabb7f74-24a1-4173-911b-26924c1be619","name":"TestAccCustomModel_DeployModelOnServer","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":56960,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:48.796286Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:35.683881Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-07T10:19:23.153808Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' + body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:14.861650Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-21T16:26:14.792208Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-05-21T16:23:31.620336Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"e7599d92-c1d4-4729-9843-63ca2d5f690d","name":"mistral/devstral-small-2505:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":94000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:23:43.338045Z"},{"created_at":"2025-05-21T16:24:34.777647Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"16c82320-33a4-4b75-a69d-172f0744d759","name":"mistral/devstral-small-2505:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:24:45.303772Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:38.997736Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' headers: Content-Length: - - "50297" + - "50533" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:01 GMT + - Tue, 27 May 2025 10:08:54 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -981,11 +1177,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - eade2eb2-d72b-4495-ac31-1dc6a52e537e + - 3fe1c584-eb6d-4ba4-aa4c-9f54dc322665 status: 200 OK code: 200 - duration: 259.126417ms - - id: 20 + duration: 361.954042ms + - id: 24 request: proto: HTTP/1.1 proto_major: 1 @@ -1000,7 +1196,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models/7205dbce-cc80-4b2a-bb7f-3fd3a804afc3 method: GET response: @@ -1020,9 +1216,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:02 GMT + - Tue, 27 May 2025 10:08:55 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1030,11 +1226,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - ee3aad49-ac77-46a7-8cd6-6e2129f85498 + - 095f1b91-59af-40ae-b69d-06ea3f19f954 status: 200 OK code: 200 - duration: 118.039125ms - - id: 21 + duration: 153.018792ms + - id: 25 request: proto: HTTP/1.1 proto_major: 1 @@ -1049,8 +1245,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/vpc/v2/regions/fr-par/private-networks/552f5c0d-40f0-4d67-bb57-727c50641ba9 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/vpc/v2/regions/fr-par/private-networks/a7baa1aa-c738-4871-b9c6-c1b069c59d24 method: GET response: proto: HTTP/2.0 @@ -1058,20 +1254,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 1057 + content_length: 1100 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:49.519324Z","dhcp_enabled":true,"id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","name":"private-network-test-inference","organization_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","subnets":[{"created_at":"2025-05-15T09:36:49.519324Z","id":"7633077d-66da-4644-bc1b-dbdf8bca995b","private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","subnet":"172.16.68.0/22","updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"},{"created_at":"2025-05-15T09:36:49.519324Z","id":"7488b8ca-80eb-42b4-aad5-a17471547dfa","private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","subnet":"fd64:badd:7710:82eb::/64","updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"}],"tags":[],"updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"}' + body: '{"created_at":"2025-05-27T09:56:50.279358Z","default_route_propagation_enabled":false,"dhcp_enabled":true,"id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","name":"private-network-test-inference","organization_id":"105bdce1-64c0-48ab-899d-868455867ecf","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","region":"fr-par","subnets":[{"created_at":"2025-05-27T09:56:50.279358Z","id":"b0c59263-2972-4d4f-9904-288650c027a4","private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","subnet":"172.16.16.0/22","updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"},{"created_at":"2025-05-27T09:56:50.279358Z","id":"72aa23a9-066b-4831-9e72-8234f5c5a948","private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","subnet":"fd5f:519c:6d46:2728::/64","updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"}],"tags":[],"updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"}' headers: Content-Length: - - "1057" + - "1100" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:02 GMT + - Tue, 27 May 2025 10:08:55 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1079,11 +1275,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - f050b449-cda7-4cd7-ade5-5c714b7ea280 + - f84f3049-487e-44fb-b8b5-4b7a44132d19 status: 200 OK code: 200 - duration: 45.185458ms - - id: 22 + duration: 127.851083ms + - id: 26 request: proto: HTTP/1.1 proto_major: 1 @@ -1098,7 +1294,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models?order_by=display_rank_asc&page_size=1000 method: GET response: @@ -1107,20 +1303,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 50297 + content_length: 50533 uncompressed: false - body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-04-28T18:48:01.860457Z","description":"","has_eula":false,"id":"a19296a6-4cef-447a-99bc-8f6c3ee30df4","name":"TestAccCustomModel_Basic","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-04-30T13:29:24.004776Z","description":"","has_eula":false,"id":"eabb7f74-24a1-4173-911b-26924c1be619","name":"TestAccCustomModel_DeployModelOnServer","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":56960,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:48.796286Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:35.683881Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-07T10:19:23.153808Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' + body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:14.861650Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-21T16:26:14.792208Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-05-21T16:23:31.620336Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"e7599d92-c1d4-4729-9843-63ca2d5f690d","name":"mistral/devstral-small-2505:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":94000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:23:43.338045Z"},{"created_at":"2025-05-21T16:24:34.777647Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"16c82320-33a4-4b75-a69d-172f0744d759","name":"mistral/devstral-small-2505:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:24:45.303772Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:38.997736Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' headers: Content-Length: - - "50297" + - "50533" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:02 GMT + - Tue, 27 May 2025 10:08:55 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1128,11 +1324,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 71d8257f-31f2-4fbb-b239-e0221a1d8456 + - 8bdf5765-3b72-4b2f-85ab-c45a9603fcc0 status: 200 OK code: 200 - duration: 173.9375ms - - id: 23 + duration: 289.117459ms + - id: 27 request: proto: HTTP/1.1 proto_major: 1 @@ -1147,7 +1343,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models/7205dbce-cc80-4b2a-bb7f-3fd3a804afc3 method: GET response: @@ -1167,9 +1363,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:02 GMT + - Tue, 27 May 2025 10:08:55 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1177,11 +1373,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 40d2f2ad-bd9c-4a2f-b720-073233fa4377 + - adfd9918-9508-4d0c-98a7-ea5a3ca4340d status: 200 OK code: 200 - duration: 56.269625ms - - id: 24 + duration: 33.745333ms + - id: 28 request: proto: HTTP/1.1 proto_major: 1 @@ -1196,8 +1392,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -1207,7 +1403,7 @@ interactions: trailer: {} content_length: 759 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-15T09:47:45.790408Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-27T10:08:07.112362Z"}' headers: Content-Length: - "759" @@ -1216,9 +1412,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:02 GMT + - Tue, 27 May 2025 10:08:55 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1226,11 +1422,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - db895643-5542-42f8-b30a-ea8b2d867cfc + - 1d2f0de5-3c9c-4695-9c94-335e3a241e2f status: 200 OK code: 200 - duration: 72.203ms - - id: 25 + duration: 123.1865ms + - id: 29 request: proto: HTTP/1.1 proto_major: 1 @@ -1245,7 +1441,56 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/ipam/v1/regions/fr-par/ips?order_by=created_at_desc&private_network_id=a7baa1aa-c738-4871-b9c6-c1b069c59d24&project_id=105bdce1-64c0-48ab-899d-868455867ecf&resource_id=57907164-e1b1-4617-8546-8c950f35e2d9&resource_type=llm_deployment + method: GET + response: + proto: HTTP/2.0 + proto_major: 2 + proto_minor: 0 + transfer_encoding: [] + trailer: {} + content_length: 550 + uncompressed: false + body: '{"ips":[{"address":"172.16.16.2/22","created_at":"2025-05-27T09:56:52.525469Z","id":"aebd6ce8-47a7-40c3-b765-050225bccbcb","is_ipv6":false,"project_id":"105bdce1-64c0-48ab-899d-868455867ecf","region":"fr-par","resource":{"id":"57907164-e1b1-4617-8546-8c950f35e2d9","mac_address":"02:00:00:28:DF:AC","name":"test-inference-deployment-endpoint-private","type":"llm_deployment"},"reverses":[],"source":{"subnet_id":"b0c59263-2972-4d4f-9904-288650c027a4"},"tags":[],"updated_at":"2025-05-27T09:59:10.209907Z","zone":null}],"total_count":1}' + headers: + Content-Length: + - "550" + Content-Security-Policy: + - default-src 'none'; frame-ancestors 'none' + Content-Type: + - application/json + Date: + - Tue, 27 May 2025 10:08:55 GMT + Server: + - Scaleway API Gateway (fr-par-1;edge01) + Strict-Transport-Security: + - max-age=63072000 + X-Content-Type-Options: + - nosniff + X-Frame-Options: + - DENY + X-Request-Id: + - 44fbb41c-18a0-45f9-a37f-3f87b3d2d9db + status: 200 OK + code: 200 + duration: 150.231875ms + - id: 30 + request: + proto: HTTP/1.1 + proto_major: 1 + proto_minor: 1 + content_length: 0 + transfer_encoding: [] + trailer: {} + host: api.scaleway.com + remote_addr: "" + request_uri: "" + body: "" + form: {} + headers: + User-Agent: + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models?order_by=display_rank_asc&page_size=1000 method: GET response: @@ -1254,20 +1499,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 50297 + content_length: 50533 uncompressed: false - body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-04-28T18:48:01.860457Z","description":"","has_eula":false,"id":"a19296a6-4cef-447a-99bc-8f6c3ee30df4","name":"TestAccCustomModel_Basic","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-04-30T13:29:24.004776Z","description":"","has_eula":false,"id":"eabb7f74-24a1-4173-911b-26924c1be619","name":"TestAccCustomModel_DeployModelOnServer","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":56960,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:48.796286Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:35.683881Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-07T10:19:23.153808Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' + body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:14.861650Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-21T16:26:14.792208Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-05-21T16:23:31.620336Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"e7599d92-c1d4-4729-9843-63ca2d5f690d","name":"mistral/devstral-small-2505:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":94000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:23:43.338045Z"},{"created_at":"2025-05-21T16:24:34.777647Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"16c82320-33a4-4b75-a69d-172f0744d759","name":"mistral/devstral-small-2505:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:24:45.303772Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:38.997736Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' headers: Content-Length: - - "50297" + - "50533" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:03 GMT + - Tue, 27 May 2025 10:08:56 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1275,11 +1520,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 3b9efb76-f970-47a0-9318-edbda24ccd0a + - f217f14f-90f1-461c-b6ee-e08d392d4027 status: 200 OK code: 200 - duration: 187.605916ms - - id: 26 + duration: 247.612125ms + - id: 31 request: proto: HTTP/1.1 proto_major: 1 @@ -1294,7 +1539,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models/7205dbce-cc80-4b2a-bb7f-3fd3a804afc3 method: GET response: @@ -1314,9 +1559,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:03 GMT + - Tue, 27 May 2025 10:08:56 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1324,11 +1569,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 4db62bcb-8b50-49aa-83bc-5ce845095d5d + - eb2bb920-ba1f-4116-9c7b-596a5b26011d status: 200 OK code: 200 - duration: 32.809167ms - - id: 27 + duration: 34.706042ms + - id: 32 request: proto: HTTP/1.1 proto_major: 1 @@ -1343,8 +1588,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/vpc/v2/regions/fr-par/private-networks/552f5c0d-40f0-4d67-bb57-727c50641ba9 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/vpc/v2/regions/fr-par/private-networks/a7baa1aa-c738-4871-b9c6-c1b069c59d24 method: GET response: proto: HTTP/2.0 @@ -1352,20 +1597,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 1057 + content_length: 1100 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:49.519324Z","dhcp_enabled":true,"id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","name":"private-network-test-inference","organization_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","subnets":[{"created_at":"2025-05-15T09:36:49.519324Z","id":"7633077d-66da-4644-bc1b-dbdf8bca995b","private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","subnet":"172.16.68.0/22","updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"},{"created_at":"2025-05-15T09:36:49.519324Z","id":"7488b8ca-80eb-42b4-aad5-a17471547dfa","private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","subnet":"fd64:badd:7710:82eb::/64","updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"}],"tags":[],"updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"}' + body: '{"created_at":"2025-05-27T09:56:50.279358Z","default_route_propagation_enabled":false,"dhcp_enabled":true,"id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","name":"private-network-test-inference","organization_id":"105bdce1-64c0-48ab-899d-868455867ecf","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","region":"fr-par","subnets":[{"created_at":"2025-05-27T09:56:50.279358Z","id":"b0c59263-2972-4d4f-9904-288650c027a4","private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","subnet":"172.16.16.0/22","updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"},{"created_at":"2025-05-27T09:56:50.279358Z","id":"72aa23a9-066b-4831-9e72-8234f5c5a948","private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","subnet":"fd5f:519c:6d46:2728::/64","updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"}],"tags":[],"updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"}' headers: Content-Length: - - "1057" + - "1100" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:03 GMT + - Tue, 27 May 2025 10:08:56 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1373,11 +1618,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 824a239c-7dca-4478-ab30-0101f9857c81 + - e3b28448-d61d-4016-a8a5-27bf7769d6c6 status: 200 OK code: 200 - duration: 32.190208ms - - id: 28 + duration: 117.605417ms + - id: 33 request: proto: HTTP/1.1 proto_major: 1 @@ -1392,7 +1637,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models?order_by=display_rank_asc&page_size=1000 method: GET response: @@ -1401,20 +1646,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 50297 + content_length: 50533 uncompressed: false - body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-04-28T18:48:01.860457Z","description":"","has_eula":false,"id":"a19296a6-4cef-447a-99bc-8f6c3ee30df4","name":"TestAccCustomModel_Basic","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-04-30T13:29:24.004776Z","description":"","has_eula":false,"id":"eabb7f74-24a1-4173-911b-26924c1be619","name":"TestAccCustomModel_DeployModelOnServer","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":56960,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:48.796286Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:35.683881Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-07T10:19:23.153808Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' + body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:14.861650Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-21T16:26:14.792208Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-05-21T16:23:31.620336Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"e7599d92-c1d4-4729-9843-63ca2d5f690d","name":"mistral/devstral-small-2505:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":94000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:23:43.338045Z"},{"created_at":"2025-05-21T16:24:34.777647Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"16c82320-33a4-4b75-a69d-172f0744d759","name":"mistral/devstral-small-2505:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:24:45.303772Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:38.997736Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' headers: Content-Length: - - "50297" + - "50533" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:03 GMT + - Tue, 27 May 2025 10:08:56 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1422,11 +1667,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 05def516-f0bb-4201-99f1-5077f2fcc3d5 + - af14a63d-0d49-4a93-b9b7-9e75c96f9226 status: 200 OK code: 200 - duration: 177.197541ms - - id: 29 + duration: 259.54475ms + - id: 34 request: proto: HTTP/1.1 proto_major: 1 @@ -1441,7 +1686,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models/7205dbce-cc80-4b2a-bb7f-3fd3a804afc3 method: GET response: @@ -1461,9 +1706,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:04 GMT + - Tue, 27 May 2025 10:08:56 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1471,11 +1716,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - a3efbe77-bce9-4323-908d-e705e3897ec9 + - a07a443f-08d5-43b6-886f-9bd6b173cafb status: 200 OK code: 200 - duration: 41.891791ms - - id: 30 + duration: 40.987708ms + - id: 35 request: proto: HTTP/1.1 proto_major: 1 @@ -1490,8 +1735,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -1501,7 +1746,7 @@ interactions: trailer: {} content_length: 759 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-15T09:47:45.790408Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-27T10:08:07.112362Z"}' headers: Content-Length: - "759" @@ -1510,9 +1755,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:04 GMT + - Tue, 27 May 2025 10:08:56 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1520,11 +1765,60 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - b0094468-b495-42dc-ae2e-c84eef7be226 + - 89ebf5c1-d52e-417c-91a7-77f97690b61e status: 200 OK code: 200 - duration: 51.463ms - - id: 31 + duration: 124.405167ms + - id: 36 + request: + proto: HTTP/1.1 + proto_major: 1 + proto_minor: 1 + content_length: 0 + transfer_encoding: [] + trailer: {} + host: api.scaleway.com + remote_addr: "" + request_uri: "" + body: "" + form: {} + headers: + User-Agent: + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/ipam/v1/regions/fr-par/ips?order_by=created_at_desc&private_network_id=a7baa1aa-c738-4871-b9c6-c1b069c59d24&project_id=105bdce1-64c0-48ab-899d-868455867ecf&resource_id=57907164-e1b1-4617-8546-8c950f35e2d9&resource_type=llm_deployment + method: GET + response: + proto: HTTP/2.0 + proto_major: 2 + proto_minor: 0 + transfer_encoding: [] + trailer: {} + content_length: 550 + uncompressed: false + body: '{"ips":[{"address":"172.16.16.2/22","created_at":"2025-05-27T09:56:52.525469Z","id":"aebd6ce8-47a7-40c3-b765-050225bccbcb","is_ipv6":false,"project_id":"105bdce1-64c0-48ab-899d-868455867ecf","region":"fr-par","resource":{"id":"57907164-e1b1-4617-8546-8c950f35e2d9","mac_address":"02:00:00:28:DF:AC","name":"test-inference-deployment-endpoint-private","type":"llm_deployment"},"reverses":[],"source":{"subnet_id":"b0c59263-2972-4d4f-9904-288650c027a4"},"tags":[],"updated_at":"2025-05-27T09:59:10.209907Z","zone":null}],"total_count":1}' + headers: + Content-Length: + - "550" + Content-Security-Policy: + - default-src 'none'; frame-ancestors 'none' + Content-Type: + - application/json + Date: + - Tue, 27 May 2025 10:08:56 GMT + Server: + - Scaleway API Gateway (fr-par-1;edge01) + Strict-Transport-Security: + - max-age=63072000 + X-Content-Type-Options: + - nosniff + X-Frame-Options: + - DENY + X-Request-Id: + - 165fa0cc-b467-4e7d-9126-6d0339d0928e + status: 200 OK + code: 200 + duration: 62.54975ms + - id: 37 request: proto: HTTP/1.1 proto_major: 1 @@ -1539,7 +1833,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models?order_by=display_rank_asc&page_size=1000 method: GET response: @@ -1548,20 +1842,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 50297 + content_length: 50533 uncompressed: false - body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-04-28T18:48:01.860457Z","description":"","has_eula":false,"id":"a19296a6-4cef-447a-99bc-8f6c3ee30df4","name":"TestAccCustomModel_Basic","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-04-30T13:29:24.004776Z","description":"","has_eula":false,"id":"eabb7f74-24a1-4173-911b-26924c1be619","name":"TestAccCustomModel_DeployModelOnServer","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":56960,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:48.796286Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:35.683881Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-07T10:19:23.153808Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' + body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:14.861650Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-21T16:26:14.792208Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-05-21T16:23:31.620336Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"e7599d92-c1d4-4729-9843-63ca2d5f690d","name":"mistral/devstral-small-2505:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":94000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:23:43.338045Z"},{"created_at":"2025-05-21T16:24:34.777647Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"16c82320-33a4-4b75-a69d-172f0744d759","name":"mistral/devstral-small-2505:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:24:45.303772Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:38.997736Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' headers: Content-Length: - - "50297" + - "50533" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:04 GMT + - Tue, 27 May 2025 10:08:57 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1569,11 +1863,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - ffdd9d3d-5d25-46eb-bd69-f28073a04be3 + - 20b117f2-8bae-470c-b368-7fe3b0c3691a status: 200 OK code: 200 - duration: 181.150459ms - - id: 32 + duration: 281.08275ms + - id: 38 request: proto: HTTP/1.1 proto_major: 1 @@ -1588,7 +1882,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models/7205dbce-cc80-4b2a-bb7f-3fd3a804afc3 method: GET response: @@ -1608,9 +1902,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:04 GMT + - Tue, 27 May 2025 10:08:57 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1618,11 +1912,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 79b41526-1bcc-412c-8fae-90aaf306732b + - 1d46d653-a7f0-464e-95f2-d423da4c9692 status: 200 OK code: 200 - duration: 29.836084ms - - id: 33 + duration: 33.936917ms + - id: 39 request: proto: HTTP/1.1 proto_major: 1 @@ -1639,8 +1933,8 @@ interactions: Content-Type: - application/json User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/vpc/v2/regions/fr-par/private-networks/552f5c0d-40f0-4d67-bb57-727c50641ba9 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/vpc/v2/regions/fr-par/private-networks/a7baa1aa-c738-4871-b9c6-c1b069c59d24 method: PATCH response: proto: HTTP/2.0 @@ -1648,20 +1942,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 1064 + content_length: 1107 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:49.519324Z","dhcp_enabled":true,"id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","name":"private-network-test-inference-public","organization_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","subnets":[{"created_at":"2025-05-15T09:36:49.519324Z","id":"7633077d-66da-4644-bc1b-dbdf8bca995b","private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","subnet":"172.16.68.0/22","updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"},{"created_at":"2025-05-15T09:36:49.519324Z","id":"7488b8ca-80eb-42b4-aad5-a17471547dfa","private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","subnet":"fd64:badd:7710:82eb::/64","updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"}],"tags":[],"updated_at":"2025-05-15T09:48:05.280018Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"}' + body: '{"created_at":"2025-05-27T09:56:50.279358Z","default_route_propagation_enabled":false,"dhcp_enabled":true,"id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","name":"private-network-test-inference-public","organization_id":"105bdce1-64c0-48ab-899d-868455867ecf","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","region":"fr-par","subnets":[{"created_at":"2025-05-27T09:56:50.279358Z","id":"b0c59263-2972-4d4f-9904-288650c027a4","private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","subnet":"172.16.16.0/22","updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"},{"created_at":"2025-05-27T09:56:50.279358Z","id":"72aa23a9-066b-4831-9e72-8234f5c5a948","private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","subnet":"fd5f:519c:6d46:2728::/64","updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"}],"tags":[],"updated_at":"2025-05-27T10:08:57.650738Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"}' headers: Content-Length: - - "1064" + - "1107" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:05 GMT + - Tue, 27 May 2025 10:08:57 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1669,11 +1963,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 32a3f7cf-3be7-4eed-9c2d-cd7963fef8c8 + - d22ab56e-2484-4dcf-bcdb-55fe16949c4a status: 200 OK code: 200 - duration: 63.36ms - - id: 34 + duration: 114.135292ms + - id: 40 request: proto: HTTP/1.1 proto_major: 1 @@ -1688,8 +1982,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/vpc/v2/regions/fr-par/private-networks/552f5c0d-40f0-4d67-bb57-727c50641ba9 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/vpc/v2/regions/fr-par/private-networks/a7baa1aa-c738-4871-b9c6-c1b069c59d24 method: GET response: proto: HTTP/2.0 @@ -1697,20 +1991,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 1064 + content_length: 1107 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:49.519324Z","dhcp_enabled":true,"id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","name":"private-network-test-inference-public","organization_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","subnets":[{"created_at":"2025-05-15T09:36:49.519324Z","id":"7633077d-66da-4644-bc1b-dbdf8bca995b","private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","subnet":"172.16.68.0/22","updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"},{"created_at":"2025-05-15T09:36:49.519324Z","id":"7488b8ca-80eb-42b4-aad5-a17471547dfa","private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","subnet":"fd64:badd:7710:82eb::/64","updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"}],"tags":[],"updated_at":"2025-05-15T09:48:05.280018Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"}' + body: '{"created_at":"2025-05-27T09:56:50.279358Z","default_route_propagation_enabled":false,"dhcp_enabled":true,"id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","name":"private-network-test-inference-public","organization_id":"105bdce1-64c0-48ab-899d-868455867ecf","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","region":"fr-par","subnets":[{"created_at":"2025-05-27T09:56:50.279358Z","id":"b0c59263-2972-4d4f-9904-288650c027a4","private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","subnet":"172.16.16.0/22","updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"},{"created_at":"2025-05-27T09:56:50.279358Z","id":"72aa23a9-066b-4831-9e72-8234f5c5a948","private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","subnet":"fd5f:519c:6d46:2728::/64","updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"}],"tags":[],"updated_at":"2025-05-27T10:08:57.650738Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"}' headers: Content-Length: - - "1064" + - "1107" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:05 GMT + - Tue, 27 May 2025 10:08:57 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1718,11 +2012,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 2594e4af-3b77-446f-9043-3542fe16a16a + - 2c2023f8-998e-4b2a-945a-70e711336e27 status: 200 OK code: 200 - duration: 44.222625ms - - id: 35 + duration: 27.550167ms + - id: 41 request: proto: HTTP/1.1 proto_major: 1 @@ -1737,8 +2031,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -1748,7 +2042,7 @@ interactions: trailer: {} content_length: 759 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-15T09:47:45.790408Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-endpoint-private","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-27T10:08:07.112362Z"}' headers: Content-Length: - "759" @@ -1757,9 +2051,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:05 GMT + - Tue, 27 May 2025 10:08:57 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1767,11 +2061,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 28235e93-aae3-4812-86dc-1f63e51da000 + - 4a932c9a-baae-4b49-afb0-61894f6c1a6b status: 200 OK code: 200 - duration: 48.87775ms - - id: 36 + duration: 106.619625ms + - id: 42 request: proto: HTTP/1.1 proto_major: 1 @@ -1788,8 +2082,8 @@ interactions: Content-Type: - application/json User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: PATCH response: proto: HTTP/2.0 @@ -1799,7 +2093,7 @@ interactions: trailer: {} content_length: 777 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":1,"status":"deploying","tags":[],"updated_at":"2025-05-15T09:48:05.451842Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":1,"status":"deploying","tags":[],"updated_at":"2025-05-27T10:08:57.928268Z"}' headers: Content-Length: - "777" @@ -1808,9 +2102,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:05 GMT + - Tue, 27 May 2025 10:08:58 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1818,11 +2112,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 5cd48683-4302-4ded-b27d-14d80c556f66 + - ffa29e02-6988-4571-bfe9-2381d43c3491 status: 200 OK code: 200 - duration: 147.388917ms - - id: 37 + duration: 207.657625ms + - id: 43 request: proto: HTTP/1.1 proto_major: 1 @@ -1837,8 +2131,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -1848,7 +2142,7 @@ interactions: trailer: {} content_length: 773 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-15T09:48:05.451842Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-27T10:08:57.928268Z"}' headers: Content-Length: - "773" @@ -1857,9 +2151,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:06 GMT + - Tue, 27 May 2025 10:08:58 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1867,11 +2161,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 5fccf032-7849-4957-94d5-d212928c1068 + - a7731d3f-b0ec-44b6-af14-cc4292e8e222 status: 200 OK code: 200 - duration: 463.668917ms - - id: 38 + duration: 137.127625ms + - id: 44 request: proto: HTTP/1.1 proto_major: 1 @@ -1886,8 +2180,57 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/ipam/v1/regions/fr-par/ips?order_by=created_at_desc&private_network_id=a7baa1aa-c738-4871-b9c6-c1b069c59d24&project_id=105bdce1-64c0-48ab-899d-868455867ecf&resource_id=57907164-e1b1-4617-8546-8c950f35e2d9&resource_type=llm_deployment + method: GET + response: + proto: HTTP/2.0 + proto_major: 2 + proto_minor: 0 + transfer_encoding: [] + trailer: {} + content_length: 564 + uncompressed: false + body: '{"ips":[{"address":"172.16.16.2/22","created_at":"2025-05-27T09:56:52.525469Z","id":"aebd6ce8-47a7-40c3-b765-050225bccbcb","is_ipv6":false,"project_id":"105bdce1-64c0-48ab-899d-868455867ecf","region":"fr-par","resource":{"id":"57907164-e1b1-4617-8546-8c950f35e2d9","mac_address":"02:00:00:28:DF:AC","name":"test-inference-deployment-basic-endpoints-private-public","type":"llm_deployment"},"reverses":[],"source":{"subnet_id":"b0c59263-2972-4d4f-9904-288650c027a4"},"tags":[],"updated_at":"2025-05-27T10:08:58.285696Z","zone":null}],"total_count":1}' + headers: + Content-Length: + - "564" + Content-Security-Policy: + - default-src 'none'; frame-ancestors 'none' + Content-Type: + - application/json + Date: + - Tue, 27 May 2025 10:08:58 GMT + Server: + - Scaleway API Gateway (fr-par-1;edge01) + Strict-Transport-Security: + - max-age=63072000 + X-Content-Type-Options: + - nosniff + X-Frame-Options: + - DENY + X-Request-Id: + - db4f7d62-4cb1-41be-83cc-3b7124896758 + status: 200 OK + code: 200 + duration: 164.304125ms + - id: 45 + request: + proto: HTTP/1.1 + proto_major: 1 + proto_minor: 1 + content_length: 0 + transfer_encoding: [] + trailer: {} + host: api.scaleway.com + remote_addr: "" + request_uri: "" + body: "" + form: {} + headers: + User-Agent: + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -1897,7 +2240,7 @@ interactions: trailer: {} content_length: 773 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-15T09:48:05.451842Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-27T10:08:57.928268Z"}' headers: Content-Length: - "773" @@ -1906,9 +2249,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:06 GMT + - Tue, 27 May 2025 10:08:58 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1916,11 +2259,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - b52fb552-1bfa-461e-841f-01ae3bba018b + - a0153c7f-0fc9-45be-9267-5e66735fe4dd status: 200 OK code: 200 - duration: 48.30675ms - - id: 39 + duration: 135.500541ms + - id: 46 request: proto: HTTP/1.1 proto_major: 1 @@ -1935,7 +2278,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models?order_by=display_rank_asc&page_size=1000 method: GET response: @@ -1944,20 +2287,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 50297 + content_length: 50533 uncompressed: false - body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-04-28T18:48:01.860457Z","description":"","has_eula":false,"id":"a19296a6-4cef-447a-99bc-8f6c3ee30df4","name":"TestAccCustomModel_Basic","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-04-30T13:29:24.004776Z","description":"","has_eula":false,"id":"eabb7f74-24a1-4173-911b-26924c1be619","name":"TestAccCustomModel_DeployModelOnServer","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":56960,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:48.796286Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:35.683881Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-07T10:19:23.153808Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' + body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:14.861650Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-21T16:26:14.792208Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-05-21T16:23:31.620336Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"e7599d92-c1d4-4729-9843-63ca2d5f690d","name":"mistral/devstral-small-2505:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":94000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:23:43.338045Z"},{"created_at":"2025-05-21T16:24:34.777647Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"16c82320-33a4-4b75-a69d-172f0744d759","name":"mistral/devstral-small-2505:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:24:45.303772Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:38.997736Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' headers: Content-Length: - - "50297" + - "50533" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:06 GMT + - Tue, 27 May 2025 10:08:58 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -1965,11 +2308,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 3f65b514-e31a-48cb-b990-5f4ab17a47f0 + - eaf2bce0-09c4-4d5f-81db-f4cc26a72c5a status: 200 OK code: 200 - duration: 188.398583ms - - id: 40 + duration: 246.124666ms + - id: 47 request: proto: HTTP/1.1 proto_major: 1 @@ -1984,7 +2327,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models/7205dbce-cc80-4b2a-bb7f-3fd3a804afc3 method: GET response: @@ -2004,9 +2347,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:06 GMT + - Tue, 27 May 2025 10:08:58 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -2014,11 +2357,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - b25970d7-be67-4b91-8e7d-7644ab41e36b + - 0da3bbc3-1df9-4a2f-a22c-419a024b9043 status: 200 OK code: 200 - duration: 29.806667ms - - id: 41 + duration: 42.731917ms + - id: 48 request: proto: HTTP/1.1 proto_major: 1 @@ -2033,8 +2376,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/vpc/v2/regions/fr-par/private-networks/552f5c0d-40f0-4d67-bb57-727c50641ba9 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/vpc/v2/regions/fr-par/private-networks/a7baa1aa-c738-4871-b9c6-c1b069c59d24 method: GET response: proto: HTTP/2.0 @@ -2042,20 +2385,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 1064 + content_length: 1107 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:49.519324Z","dhcp_enabled":true,"id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","name":"private-network-test-inference-public","organization_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","subnets":[{"created_at":"2025-05-15T09:36:49.519324Z","id":"7633077d-66da-4644-bc1b-dbdf8bca995b","private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","subnet":"172.16.68.0/22","updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"},{"created_at":"2025-05-15T09:36:49.519324Z","id":"7488b8ca-80eb-42b4-aad5-a17471547dfa","private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","subnet":"fd64:badd:7710:82eb::/64","updated_at":"2025-05-15T09:36:49.519324Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"}],"tags":[],"updated_at":"2025-05-15T09:48:05.280018Z","vpc_id":"e092f3d5-d85b-46fd-8d08-025e3282c8c1"}' + body: '{"created_at":"2025-05-27T09:56:50.279358Z","default_route_propagation_enabled":false,"dhcp_enabled":true,"id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","name":"private-network-test-inference-public","organization_id":"105bdce1-64c0-48ab-899d-868455867ecf","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","region":"fr-par","subnets":[{"created_at":"2025-05-27T09:56:50.279358Z","id":"b0c59263-2972-4d4f-9904-288650c027a4","private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","subnet":"172.16.16.0/22","updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"},{"created_at":"2025-05-27T09:56:50.279358Z","id":"72aa23a9-066b-4831-9e72-8234f5c5a948","private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","subnet":"fd5f:519c:6d46:2728::/64","updated_at":"2025-05-27T09:56:50.279358Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"}],"tags":[],"updated_at":"2025-05-27T10:08:57.650738Z","vpc_id":"8feba4f5-79f9-42cd-b5ce-3ed8c510569e"}' headers: Content-Length: - - "1064" + - "1107" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:07 GMT + - Tue, 27 May 2025 10:08:59 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -2063,11 +2406,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 526e3e5d-f96f-47af-9642-9ad4c25a663a + - 99a0733c-c467-41c2-a4bb-943ab50b655c status: 200 OK code: 200 - duration: 24.071542ms - - id: 42 + duration: 125.901167ms + - id: 49 request: proto: HTTP/1.1 proto_major: 1 @@ -2082,7 +2425,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models?order_by=display_rank_asc&page_size=1000 method: GET response: @@ -2091,20 +2434,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 50297 + content_length: 50533 uncompressed: false - body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-04-28T18:48:01.860457Z","description":"","has_eula":false,"id":"a19296a6-4cef-447a-99bc-8f6c3ee30df4","name":"TestAccCustomModel_Basic","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-04-30T13:29:24.004776Z","description":"","has_eula":false,"id":"eabb7f74-24a1-4173-911b-26924c1be619","name":"TestAccCustomModel_DeployModelOnServer","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":56960,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:48.796286Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:35.683881Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-07T10:19:23.153808Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' + body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:14.861650Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-21T16:26:14.792208Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-05-21T16:23:31.620336Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"e7599d92-c1d4-4729-9843-63ca2d5f690d","name":"mistral/devstral-small-2505:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":94000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:23:43.338045Z"},{"created_at":"2025-05-21T16:24:34.777647Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"16c82320-33a4-4b75-a69d-172f0744d759","name":"mistral/devstral-small-2505:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:24:45.303772Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:38.997736Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' headers: Content-Length: - - "50297" + - "50533" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:07 GMT + - Tue, 27 May 2025 10:08:59 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -2112,11 +2455,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 497f4786-123e-41ca-afd1-2f5fe63bdf1b + - a119ea4b-e06a-445b-b508-51a78265456a status: 200 OK code: 200 - duration: 173.929292ms - - id: 43 + duration: 283.193417ms + - id: 50 request: proto: HTTP/1.1 proto_major: 1 @@ -2131,7 +2474,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models/7205dbce-cc80-4b2a-bb7f-3fd3a804afc3 method: GET response: @@ -2151,9 +2494,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:07 GMT + - Tue, 27 May 2025 10:08:59 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -2161,11 +2504,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 1fa2ef90-a240-4ae3-a98a-810532512650 + - a96a0243-8e89-4d2a-8a96-70110d100fa6 status: 200 OK code: 200 - duration: 32.686833ms - - id: 44 + duration: 35.094834ms + - id: 51 request: proto: HTTP/1.1 proto_major: 1 @@ -2180,8 +2523,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -2191,7 +2534,7 @@ interactions: trailer: {} content_length: 773 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-15T09:48:05.451842Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-27T10:08:57.928268Z"}' headers: Content-Length: - "773" @@ -2200,9 +2543,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:07 GMT + - Tue, 27 May 2025 10:08:59 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -2210,11 +2553,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - bed8e69e-9ce9-44f7-a1e1-8be5e67b53e2 + - 26d7ca07-fa07-459c-9ba8-5d7a9525fab3 status: 200 OK code: 200 - duration: 45.067375ms - - id: 45 + duration: 132.818583ms + - id: 52 request: proto: HTTP/1.1 proto_major: 1 @@ -2229,7 +2572,56 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/ipam/v1/regions/fr-par/ips?order_by=created_at_desc&private_network_id=a7baa1aa-c738-4871-b9c6-c1b069c59d24&project_id=105bdce1-64c0-48ab-899d-868455867ecf&resource_id=57907164-e1b1-4617-8546-8c950f35e2d9&resource_type=llm_deployment + method: GET + response: + proto: HTTP/2.0 + proto_major: 2 + proto_minor: 0 + transfer_encoding: [] + trailer: {} + content_length: 564 + uncompressed: false + body: '{"ips":[{"address":"172.16.16.2/22","created_at":"2025-05-27T09:56:52.525469Z","id":"aebd6ce8-47a7-40c3-b765-050225bccbcb","is_ipv6":false,"project_id":"105bdce1-64c0-48ab-899d-868455867ecf","region":"fr-par","resource":{"id":"57907164-e1b1-4617-8546-8c950f35e2d9","mac_address":"02:00:00:28:DF:AC","name":"test-inference-deployment-basic-endpoints-private-public","type":"llm_deployment"},"reverses":[],"source":{"subnet_id":"b0c59263-2972-4d4f-9904-288650c027a4"},"tags":[],"updated_at":"2025-05-27T10:08:58.285696Z","zone":null}],"total_count":1}' + headers: + Content-Length: + - "564" + Content-Security-Policy: + - default-src 'none'; frame-ancestors 'none' + Content-Type: + - application/json + Date: + - Tue, 27 May 2025 10:08:59 GMT + Server: + - Scaleway API Gateway (fr-par-1;edge01) + Strict-Transport-Security: + - max-age=63072000 + X-Content-Type-Options: + - nosniff + X-Frame-Options: + - DENY + X-Request-Id: + - c04929a1-548f-41a9-aa2f-a1519db7a1c4 + status: 200 OK + code: 200 + duration: 55.871875ms + - id: 53 + request: + proto: HTTP/1.1 + proto_major: 1 + proto_minor: 1 + content_length: 0 + transfer_encoding: [] + trailer: {} + host: api.scaleway.com + remote_addr: "" + request_uri: "" + body: "" + form: {} + headers: + User-Agent: + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models?order_by=display_rank_asc&page_size=1000 method: GET response: @@ -2238,20 +2630,20 @@ interactions: proto_minor: 0 transfer_encoding: [] trailer: {} - content_length: 50297 + content_length: 50533 uncompressed: false - body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-04-28T18:48:01.860457Z","description":"","has_eula":false,"id":"a19296a6-4cef-447a-99bc-8f6c3ee30df4","name":"TestAccCustomModel_Basic","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-04-30T13:29:24.004776Z","description":"","has_eula":false,"id":"eabb7f74-24a1-4173-911b-26924c1be619","name":"TestAccCustomModel_DeployModelOnServer","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100","quantizations":[{"allowed":true,"max_context_size":18615,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]},{"node_type_name":"H100-2","quantizations":[{"allowed":true,"max_context_size":131072,"quantization_bits":32},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":4}]}]}],"parameter_size_bits":32,"project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","region":"fr-par","size_bytes":59091725346,"status":"ready","tags":["custom"],"updated_at":null},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":56960,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:48.796286Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:35.683881Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-07T10:19:23.153808Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' + body: '{"models":[{"created_at":"2025-04-04T13:11:00.900800Z","description":"Multimodal model for text generation an image understanding supporting up to 128k context window.","has_eula":false,"id":"5c40e594-d40d-452a-991e-5082225155e1","name":"google/gemma-3-27b-it:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":80000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":54904369444,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T16:45:10.128397Z"},{"created_at":"2025-03-27T16:48:11.513249Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"a51ce791-9546-4c28-aa44-24850d84778b","name":"deepseek/deepseek-r1-distill-llama-8b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":true,"max_context_size":39000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":16070465043,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:49.797687Z"},{"created_at":"2025-03-27T16:48:14.190404Z","description":"Efficient 8B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"b8dc7f2d-95d6-48ae-a076-a99e76b76e1f","name":"deepseek/deepseek-r1-distill-llama-8b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":90000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9093169346,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-04-14T09:05:26.354374Z"},{"created_at":"2025-04-04T15:51:25.414165Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"efcf0b60-999a-4c1e-981e-b68a428c4702","name":"mistral/mistral-small-3.1-24b-instruct-2503:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":75000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-05-09T13:51:56.986698Z"},{"created_at":"2025-04-04T15:51:27.773573Z","description":"Highly efficient multimodal model with vision and chat capabilities supporting up to 128k context window.","has_eula":false,"id":"906c0feb-0eb0-4037-94aa-afd4d845b94f","name":"mistral/mistral-small-3.1-24b-instruct-2503:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":96077777613,"status":"ready","tags":["instruct","chat","vision","featured"],"updated_at":"2025-04-08T14:26:24.388332Z"},{"created_at":"2025-03-27T16:47:41.108667Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"014919c1-00cc-43c2-98f2-4ffd263e6f33","name":"deepseek/deepseek-r1-distill-llama-70b:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":141117442445,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:14.861650Z"},{"created_at":"2025-03-27T16:47:42.762505Z","description":"Efficient 70B-param distilled model by DeepSeek, balancing performance and compactness.","has_eula":true,"id":"bbfeeb62-2428-415d-ad0d-537af9aff946","name":"deepseek/deepseek-r1-distill-llama-70b:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679175005,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-21T16:26:14.792208Z"},{"created_at":"2025-03-27T16:48:40.045689Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","name":"meta/llama-3.1-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":true,"max_context_size":40000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132582323,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:53.288962Z"},{"created_at":"2025-03-27T16:50:12.267422Z","description":"Highly advanced coding model with a 128k context window, excelling in code generation, repairing, and reasoning.","has_eula":false,"id":"a3205fd3-ac4a-47cf-9074-82166d214bac","name":"qwen/qwen2.5-coder-32b-instruct:int8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":35080374444,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-09T13:52:04.105122Z"},{"created_at":"2025-05-21T16:23:31.620336Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"e7599d92-c1d4-4729-9843-63ca2d5f690d","name":"mistral/devstral-small-2505:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":94000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:23:43.338045Z"},{"created_at":"2025-05-21T16:24:34.777647Z","description":"Devstral is an agentic LLM for software engineering tasks.","has_eula":false,"id":"16c82320-33a4-4b75-a69d-172f0744d759","name":"mistral/devstral-small-2505:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":true,"max_context_size":131072,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94305992547,"status":"ready","tags":["instruct","chat","code","featured"],"updated_at":"2025-05-21T16:24:45.303772Z"},{"created_at":"2025-03-27T16:49:51.968791Z","description":"A large language model customized by NVIDIA in order to improve the helpfulness of generated responses.","has_eula":true,"id":"4e6c9cea-57a1-4215-8a11-24ab51b9d1c8","name":"nvidia/llama-3.1-nemotron-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72679219797,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:01.331740Z"},{"created_at":"2025-05-13T12:13:50.994Z","description":"Best-in-class vision language model by research lab Allen Institute for AI. Available under the Apache 2.0 license.","has_eula":false,"id":"864e7786-4b86-4f4b-8534-25da1fc46a74","name":"allenai/molmo-72b-0924:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":45000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":293245208984,"status":"ready","tags":["instruct","chat","vision"],"updated_at":"2025-05-13T13:34:01.318606Z"},{"created_at":"2025-03-27T16:49:37.342054Z","description":"Efficient 8B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"775cbef7-6527-415d-9e6b-39d574cf39ec","name":"meta/llama-3.1-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":93000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090504772,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:00.700210Z"},{"created_at":"2025-03-27T16:48:15.818596Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"bc10c88e-4d18-4854-8250-77aff4763eca","name":"meta/llama-3-8b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":true,"max_context_size":8192,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":32132572668,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:51.995701Z"},{"created_at":"2025-03-27T16:49:33.359621Z","description":"First generation of 8B-param model by Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b5a94646-9390-4ced-acba-9b078e63a794","name":"meta/llama-3-8b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":9090489355,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:59.473065Z"},{"created_at":"2025-03-27T16:48:42.138410Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"126ad0c4-cfde-4b05-924f-f04c6343ccb2","name":"meta/llama-3.3-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":45000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282254830887,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:53.868968Z"},{"created_at":"2025-03-27T16:50:09.605796Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"1678195b-5af6-4c27-8fdc-16aa84c68c34","name":"meta/llama-3.3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72687332869,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-23T15:30:38.997736Z"},{"created_at":"2025-03-27T16:48:35.312110Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"7cbe0417-172a-4601-8940-3b71e4d0c8cb","name":"meta/llama-3.1-70b-instruct:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":60000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":282246710880,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:52.677798Z"},{"created_at":"2025-03-27T16:49:35.836269Z","description":"Efficient 70B-param model by Meta, optimized for multilingual dialogue.","has_eula":true,"id":"03150ad5-de83-4c74-afe0-3eeeb67d71a3","name":"meta/llama-3.1-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":15000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":131072,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665889083,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:52:00.003235Z"},{"created_at":"2025-03-27T16:49:31.715567Z","description":"First generation of 70B-param model from Meta, fine-tuned for instruction and automation.","has_eula":true,"id":"b0c5a8fe-5c9e-49cc-942a-6c4ebaadde67","name":"meta/llama-3-70b-instruct:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":8192,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":72665872089,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:58.899458Z"},{"created_at":"2025-03-27T16:49:17.458153Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"1e555754-47fb-4dba-a82c-66f3f1fa9294","name":"mistral/mistral-small-24b-instruct-2501:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":94321843451,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.176379Z"},{"created_at":"2025-03-27T16:50:07.300436Z","description":"A state-of-the-art 24B model with a 32k context window, designed for multilingual chat and agentic applications.","has_eula":false,"id":"7bb28f2c-3719-4d71-9bcb-17db392a7118","name":"mistral/mistral-small-24b-instruct-2501:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":20000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":24938988520,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-09T13:51:55.726891Z"},{"created_at":"2025-04-15T10:51:31.291792Z","description":"Vision language model able to analyze images and offer insights without compromising on instruction following.","has_eula":false,"id":"1999f4f5-f038-4039-94ba-11a851917df5","name":"mistral/pixtral-12b-2409:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":50000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":true,"max_context_size":128000,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":25384844091,"status":"ready","tags":["vision","chat","featured"],"updated_at":"2025-05-09T13:51:58.281971Z"},{"created_at":"2025-03-27T16:49:14.593008Z","description":"A very efficient language model by Mistral AI, optimized for instruction-following tasks. Available under the Apache 2.0 license.","has_eula":false,"id":"bf6be106-c53d-4b93-bb33-1a4bd4d0b573","name":"mistral/mistral-7b-instruct-v0.3:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":28995471292,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:54.595513Z"},{"created_at":"2025-03-27T16:50:06.301430Z","description":"A state-of-the-art 12B model with a 128k context window, designed for multilingual chat applications.","has_eula":false,"id":"07681325-c743-4796-8b7d-1f0b35d4a8e0","name":"mistral/mistral-nemo-instruct-2407:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":128000,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":13605604415,"status":"ready","tags":["instruct","chat","featured"],"updated_at":"2025-05-06T15:17:43.837103Z"},{"created_at":"2025-03-27T16:50:08.291821Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"1aa87d1e-9996-4c54-aa1c-5b900bf59fd4","name":"mistral/mixtral-8x7b-instruct-v0.1:fp8","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":8,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":46970879717,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:52:02.960404Z"},{"created_at":"2025-03-27T16:49:19.120192Z","description":"A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI, licensed under Apache 2.0.","has_eula":false,"id":"11ed6599-f460-4e41-b266-87bc9a108fdd","name":"mistral/mixtral-8x7b-instruct-v0.1:bf16","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":true,"max_context_size":32768,"quantization_bits":8},{"allowed":true,"max_context_size":32768,"quantization_bits":16},{"allowed":false,"max_context_size":0,"quantization_bits":32}]}]}],"parameter_size_bits":16,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":190483875108,"status":"ready","tags":["instruct","chat"],"updated_at":"2025-05-09T13:51:57.661626Z"},{"created_at":"2025-03-27T16:46:54.314987Z","description":"An embedding model spanning a broad range of languages and state-of-the-art results on multilingual benchmarks.","has_eula":true,"id":"d58efec4-b667-48e2-8ad8-bcc26c175ae6","name":"baai/bge-multilingual-gemma2:fp32","nodes_support":[{"nodes":[{"node_type_name":"L4","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"L40S","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]},{"node_type_name":"H100-2","quantizations":[{"allowed":false,"max_context_size":0,"quantization_bits":4},{"allowed":false,"max_context_size":0,"quantization_bits":8},{"allowed":false,"max_context_size":0,"quantization_bits":16},{"allowed":true,"max_context_size":8192,"quantization_bits":32}]}]}],"parameter_size_bits":32,"project_id":"00000000-0000-0000-0000-000000000000","region":"fr-par","size_bytes":36989461520,"status":"ready","tags":["embedding","featured"],"updated_at":"2025-03-27T17:40:09.534954Z"}],"total_count":29}' headers: Content-Length: - - "50297" + - "50533" Content-Security-Policy: - default-src 'none'; frame-ancestors 'none' Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:07 GMT + - Tue, 27 May 2025 10:08:59 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -2259,11 +2651,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - d1162d15-be00-4801-b9fc-efcbcff76ee7 + - cad3f446-7e11-46a2-9db7-a7f857ac2181 status: 200 OK code: 200 - duration: 176.634125ms - - id: 46 + duration: 284.96275ms + - id: 54 request: proto: HTTP/1.1 proto_major: 1 @@ -2278,7 +2670,7 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests url: https://api.scaleway.com/inference/v1/regions/fr-par/models/7205dbce-cc80-4b2a-bb7f-3fd3a804afc3 method: GET response: @@ -2298,9 +2690,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:07 GMT + - Tue, 27 May 2025 10:08:59 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -2308,11 +2700,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 9a07cad4-f153-4c51-92b0-c3ffd2609f1d + - 7ae85682-1e7e-467c-94f6-624f54e37185 status: 200 OK code: 200 - duration: 29.628834ms - - id: 47 + duration: 38.133334ms + - id: 55 request: proto: HTTP/1.1 proto_major: 1 @@ -2327,8 +2719,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -2338,7 +2730,7 @@ interactions: trailer: {} content_length: 777 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":1,"status":"deploying","tags":[],"updated_at":"2025-05-15T09:48:07.477689Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":1,"status":"deploying","tags":[],"updated_at":"2025-05-27T10:08:59.931028Z"}' headers: Content-Length: - "777" @@ -2347,9 +2739,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:48:08 GMT + - Tue, 27 May 2025 10:09:00 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -2357,11 +2749,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - d525b0ee-a31c-4322-a243-55c4118de079 + - 704a2c07-c633-4ba3-8221-5849d39c9865 status: 200 OK code: 200 - duration: 43.001375ms - - id: 48 + duration: 121.851625ms + - id: 56 request: proto: HTTP/1.1 proto_major: 1 @@ -2376,8 +2768,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -2387,7 +2779,7 @@ interactions: trailer: {} content_length: 777 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":1,"status":"deploying","tags":[],"updated_at":"2025-05-15T09:48:07.477689Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":1,"status":"deploying","tags":[],"updated_at":"2025-05-27T10:08:59.931028Z"}' headers: Content-Length: - "777" @@ -2396,9 +2788,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:49:08 GMT + - Tue, 27 May 2025 10:10:00 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge01) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -2406,11 +2798,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - e6edcbf3-edd8-4a69-ba0c-a8b49d95dfef + - 01286a90-c9fb-44f6-9d82-d518391e7fb2 status: 200 OK code: 200 - duration: 99.261375ms - - id: 49 + duration: 206.144667ms + - id: 57 request: proto: HTTP/1.1 proto_major: 1 @@ -2425,8 +2817,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -2436,7 +2828,7 @@ interactions: trailer: {} content_length: 777 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":1,"status":"deploying","tags":[],"updated_at":"2025-05-15T09:48:07.477689Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":1,"status":"deploying","tags":[],"updated_at":"2025-05-27T10:08:59.931028Z"}' headers: Content-Length: - "777" @@ -2445,9 +2837,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:50:09 GMT + - Tue, 27 May 2025 10:11:00 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge02) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -2455,11 +2847,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - fb2b61f0-04c3-4cff-a06c-3e2d95b4630a + - f3523d08-c8d8-4600-ad94-05d4589e0939 status: 200 OK code: 200 - duration: 100.894333ms - - id: 50 + duration: 184.931708ms + - id: 58 request: proto: HTTP/1.1 proto_major: 1 @@ -2474,8 +2866,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -2485,7 +2877,7 @@ interactions: trailer: {} content_length: 773 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-15T09:50:15.710830Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":1,"status":"ready","tags":[],"updated_at":"2025-05-27T10:11:06.777211Z"}' headers: Content-Length: - "773" @@ -2494,9 +2886,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:51:09 GMT + - Tue, 27 May 2025 10:12:00 GMT Server: - - Scaleway API Gateway (fr-par-2;edge01) + - Scaleway API Gateway (fr-par-1;edge03) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -2504,11 +2896,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 9c33278f-b521-4c41-94aa-5fb335efdf64 + - 99da0e15-9e1a-4b38-acb8-dc20699270e1 status: 200 OK code: 200 - duration: 147.120583ms - - id: 51 + duration: 204.791167ms + - id: 59 request: proto: HTTP/1.1 proto_major: 1 @@ -2523,8 +2915,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: DELETE response: proto: HTTP/2.0 @@ -2534,7 +2926,7 @@ interactions: trailer: {} content_length: 776 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":1,"status":"deleting","tags":[],"updated_at":"2025-05-15T09:50:15.710830Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":1,"status":"deleting","tags":[],"updated_at":"2025-05-27T10:11:06.777211Z"}' headers: Content-Length: - "776" @@ -2543,9 +2935,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:51:09 GMT + - Tue, 27 May 2025 10:12:01 GMT Server: - - Scaleway API Gateway (fr-par-2;edge01) + - Scaleway API Gateway (fr-par-1;edge03) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -2553,11 +2945,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 120a0bbe-cac6-4a2b-b274-d6c0883a8c56 + - 2647b3a4-f943-4ac2-9769-1e813db9ec74 status: 200 OK code: 200 - duration: 139.438042ms - - id: 52 + duration: 231.3645ms + - id: 60 request: proto: HTTP/1.1 proto_major: 1 @@ -2572,8 +2964,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -2583,7 +2975,7 @@ interactions: trailer: {} content_length: 776 uncompressed: false - body: '{"created_at":"2025-05-15T09:36:50.092088Z","endpoints":[{"disable_auth":false,"id":"60f26766-a204-48cb-8e51-907a62dd69d0","private_network":{"private_network_id":"552f5c0d-40f0-4d67-bb57-727c50641ba9"},"url":"https://986d6dc6-3514-4780-b64b-d8f214ef1757.552f5c0d-40f0-4d67-bb57-727c50641ba9.internal"}],"error_message":"","id":"986d6dc6-3514-4780-b64b-d8f214ef1757","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"d3520a52-2c75-4ba0-bda8-82dd087f07f2","quantization":{"bits":16},"region":"fr-par","size":1,"status":"deleting","tags":[],"updated_at":"2025-05-15T09:50:15.710830Z"}' + body: '{"created_at":"2025-05-27T09:56:50.916374Z","endpoints":[{"disable_auth":false,"id":"444d9500-cf86-4651-9c67-90604fd0f183","private_network":{"private_network_id":"a7baa1aa-c738-4871-b9c6-c1b069c59d24"},"url":"https://57907164-e1b1-4617-8546-8c950f35e2d9.a7baa1aa-c738-4871-b9c6-c1b069c59d24.internal"}],"error_message":"","id":"57907164-e1b1-4617-8546-8c950f35e2d9","max_size":1,"min_size":1,"model_id":"7205dbce-cc80-4b2a-bb7f-3fd3a804afc3","model_name":"meta/llama-3.1-8b-instruct:bf16","name":"test-inference-deployment-basic-endpoints-private-public","node_type_name":"L4","project_id":"105bdce1-64c0-48ab-899d-868455867ecf","quantization":{"bits":16},"region":"fr-par","size":1,"status":"deleting","tags":[],"updated_at":"2025-05-27T10:11:06.777211Z"}' headers: Content-Length: - "776" @@ -2592,9 +2984,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:51:09 GMT + - Tue, 27 May 2025 10:12:01 GMT Server: - - Scaleway API Gateway (fr-par-2;edge01) + - Scaleway API Gateway (fr-par-1;edge03) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -2602,11 +2994,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 9c01d0a0-283f-4cc1-a981-0355b3d24b08 + - 3b4b1899-d7d5-4729-8981-45e4adba9a0e status: 200 OK code: 200 - duration: 58.92075ms - - id: 53 + duration: 123.344333ms + - id: 61 request: proto: HTTP/1.1 proto_major: 1 @@ -2621,8 +3013,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -2632,7 +3024,7 @@ interactions: trailer: {} content_length: 131 uncompressed: false - body: '{"message":"resource is not found","resource":"deployment","resource_id":"986d6dc6-3514-4780-b64b-d8f214ef1757","type":"not_found"}' + body: '{"message":"resource is not found","resource":"deployment","resource_id":"57907164-e1b1-4617-8546-8c950f35e2d9","type":"not_found"}' headers: Content-Length: - "131" @@ -2641,9 +3033,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:52:09 GMT + - Tue, 27 May 2025 10:13:01 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge03) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -2651,11 +3043,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 975d76f0-da30-4483-a366-e01bc71339c4 + - 62fc6082-c615-4d42-ab4a-03c9c4e7a6b6 status: 404 Not Found code: 404 - duration: 63.447792ms - - id: 54 + duration: 70.863208ms + - id: 62 request: proto: HTTP/1.1 proto_major: 1 @@ -2670,8 +3062,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/vpc/v2/regions/fr-par/private-networks/552f5c0d-40f0-4d67-bb57-727c50641ba9 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/vpc/v2/regions/fr-par/private-networks/a7baa1aa-c738-4871-b9c6-c1b069c59d24 method: DELETE response: proto: HTTP/2.0 @@ -2688,9 +3080,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:52:10 GMT + - Tue, 27 May 2025 10:13:02 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge03) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -2698,11 +3090,11 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 51412238-2aca-41a4-8c5f-51b8b6e416df + - 06f696df-9b3e-41fb-bbb8-998dbe778dc6 status: 204 No Content code: 204 - duration: 1.734887375s - - id: 55 + duration: 1.395089375s + - id: 63 request: proto: HTTP/1.1 proto_major: 1 @@ -2717,8 +3109,8 @@ interactions: form: {} headers: User-Agent: - - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.1; darwin; arm64) terraform-provider/develop terraform/terraform-tests - url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/986d6dc6-3514-4780-b64b-d8f214ef1757 + - scaleway-sdk-go/v1.0.0-beta.7+dev (go1.24.2; darwin; arm64) terraform-provider/develop terraform/terraform-tests + url: https://api.scaleway.com/inference/v1/regions/fr-par/deployments/57907164-e1b1-4617-8546-8c950f35e2d9 method: GET response: proto: HTTP/2.0 @@ -2728,7 +3120,7 @@ interactions: trailer: {} content_length: 131 uncompressed: false - body: '{"message":"resource is not found","resource":"deployment","resource_id":"986d6dc6-3514-4780-b64b-d8f214ef1757","type":"not_found"}' + body: '{"message":"resource is not found","resource":"deployment","resource_id":"57907164-e1b1-4617-8546-8c950f35e2d9","type":"not_found"}' headers: Content-Length: - "131" @@ -2737,9 +3129,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 May 2025 09:52:11 GMT + - Tue, 27 May 2025 10:13:02 GMT Server: - - Scaleway API Gateway (fr-par-2;edge02) + - Scaleway API Gateway (fr-par-1;edge03) Strict-Transport-Security: - max-age=63072000 X-Content-Type-Options: @@ -2747,7 +3139,7 @@ interactions: X-Frame-Options: - DENY X-Request-Id: - - 0a23b017-edbc-463d-ac44-7c038765b509 + - abb3a5f0-19e5-4540-9c04-8b37e4cad75d status: 404 Not Found code: 404 - duration: 32.897583ms + duration: 27.318ms