Codex Rust: now way to provide api version for azure provider

Resolved 💬 5 comments Opened Jun 12, 2025 by da1z Closed Sep 24, 2025

What version of Codex is running?

codex-cli 0.0.2505291458

Which model were you using?

What platform is your computer?

Darwin 24.5.0 arm64 arm

What steps can reproduce the bug?

model = "gpt-4o"
model_provider = "azure"

[model_providers.azure]
name = "Azure"
base_url = "https://resource.openai.azure.com/openai/v1"
wire_api = "chat"
env_key = "OPENAI_API_KEY"

will fail with: API in preview mode, please use api-version=preview.
need to provide api-version in queryParams

What is the expected behavior?

works?

What do you see instead?

API in preview mode, please use api-version=preview.

Additional information

_No response_

View original on GitHub ↗

5 Comments

da1z · 1 year ago

workaround for now is to put full url and #

base_url = "https://<myresource>.azure.com/openai/responses?api-version=2025-04-01-preview#"

da1z · 1 year ago

can be fixed by https://github.com/openai/codex/pull/1319

vvvlad · 1 year ago

@da1z
I'm having the same issue, and your workaround worked great for me!
Hope there will be a permanent fix soon.

Thank you!

ksquarekumar · 11 months ago

model = "<YOUR-DEPLOYMENT-NAME>"
model_provider = "<YOUR-PROVIDER-NAME>"
profile = "<YOUR-PROFILE-NAME>"

[model_providers."<YOUR-PROVIDER-NAME>"]
name = "Azure"
base_url = "https://<YOUR-RESOURCE-NAME>.openai.azure.com/openai/v1/"
env_key = "AZURE_OPENAI_API_KEY"
wire_api = "responses" # Changed from "chat", works as of v1 api GA, recommende
request_max_retries = 4
stream_max_retries = 10
stream_idle_timeout_ms = 300000

[profiles."<YOUR-PROFILE-NAME>"]
model = "<YOUR-DEPLOYMENT-NAME>"
model_provider = "<YOUR-PROVIDER-NAME>"

Works for me, and resolves the need to specify API Versions

don't pick from /models though else it gives ⚠️ stream error: unexpected status 404 Not Found: {"error":{"code":"DeploymentNotFound"...}} errors.

da1z · 11 months ago

looks like it was fixed in some recent releases