Azure OpenAI custom model not working in VSCode Chat

[bahtman]

Type: Bug

Select custom model.
Type model name
Type Azure OpenAI deployment url

Get following error:
Could not extract deployment name from the Azure endpoint URL. Please ensure it follows the format https://.openai.azure.com/

VS Code version: Code 1.100.2 (848b80aeb52026648a8ff9f7c45a9b0a80641e2e, 2025-05-14T21:47:40.416Z)
OS version: Windows_NT x64 10.0.26100
Modes:

System Info

Item	Value
CPUs	AMD Ryzen 7 5800X3D 8-Core Processor (16 x 3394)
GPU Status	2d_canvas: enabled canvas_oop_rasterization: enabled_on direct_rendering_display_compositor: disabled_off_ok gpu_compositing: enabled multiple_raster_threads: enabled_on opengl: enabled_on rasterization: enabled raw_draw: disabled_off_ok skia_graphite: disabled_off video_decode: enabled video_encode: enabled vulkan: disabled_off webgl: enabled webgl2: enabled webgpu: enabled webnn: disabled_off
Load (avg)	undefined
Memory (System)	31.91GB (17.58GB free)
Process Argv	--crash-reporter-id 4eb59ac9-f15c-4434-acb6-e2ac6e868043
Screen Reader	no
VM	0%

Extensions (12)

Extension	Author (truncated)	Version
ruff	cha	2025.22.0
copilot	Git	1.323.1580
copilot-chat	Git	0.27.2
go	gol	0.46.1
debugpy	ms-	2025.8.0
python	ms-	2025.6.1
vscode-pylance	ms-	2025.5.1
jupyter	ms-	2025.4.1
jupyter-keymap	ms-	1.1.2
jupyter-renderers	ms-	1.1.0
vscode-jupyter-cell-tags	ms-	0.1.9
vscode-jupyter-slideshow	ms-	0.1.6

A/B Experiments

vsliv368cf:30146710
vspor879:30202332
vspor708:30202333
vspor363:30204092
vscod805cf:30301675
binariesv615:30325510
vscaat:30438848
c4g48928:30535728
azure-dev_surveyone:30548225
a9j8j154:30646983
962ge761:30959799
h48ei257:31000450
pythontbext0:30879054
cppperfnew:31000557
dwnewjupyter:31046869
pythonrstrctxt:31112756
nativeloc1:31192215
5fd0e150:31155592
dwcopilot:31170013
6074i472:31201624
dwoutputs:31242946
customenabled:31248079
hdaa2157:31222309
copilot_t_ci:31222730
e5gg6876:31282496
pythoneinst12:31285622
bgtreat:31268568
4gafe986:31271826
9gig6300:31313792
6gi0g917:31259952
996jf627:31283433
pythonrdcb7:31303018
usemplatestapi:31297334
0aa6g176:31307128
7bj51361:31289155
747dc170:31275177
pylancecolor:31314202
aj953862:31281341
generatesymbolt:31295002
convertfstringf:31295003
gendocf:31295004

[bahtman]

Hi @isidorn
As promised here is the issue described :)

[isidorn]

Thanks for filling. Assigning to @lramos15 to get his thoughts

[lramos15]

This should be fixed in Insiders if you give a try. Let me know if you have issues there

[bahtman]

Hi @lramos15,

Cheers for the quick response. That solved that issue.
From what I can tell the only authentication method is an API key. My organisation does not allow that. Is it possible to utilize Azure Identity for this?

[bahtman]

I also just noticed when attempting to add a secondary model I am not asked for the model name.
This results in the following error

[bahtman]

Do tell if I should open seperate issues. When I added my custom azure model. Default settings does not allow the model (gpt 4.1) to be used in agent mode. I assume this is linked with the tool calling / image understand questions in custom settings. This would be nice to have a bit more clear.

[lramos15]

From what I can tell the only authentication method is an API key. My organisation does not allow that. Is it possible to utilize Azure Identity for this?

Not at this time, but it is in on the backlog

I also just noticed when attempting to add a secondary model I am not asked for the model name.

Odd, I will take a look

I assume this is linked with the tool calling / image understand questions in custom settings

Yeah tool calling is needed for agent

[bahtman]

From what I can tell the only authentication method is an API key. My organisation does not allow that. Is it possible to utilize Azure Identity for this?

Not at this time, but it is in on the backlog

Really looking forward to this. Thank you very much for the replies. Have a great weekend.