[Bug]: copilot gpt-5-codex and gpt-5.1-codex don't work

[msexxeta]

What happened?

When trying to add the codex models from copilot:

  - model_name: copilot-gpt-5.1-codex
    litellm_params:
      model: github_copilot/gpt-5.1-codex
      extra_headers: {"Editor-Version": "vscode/1.85.1", "Copilot-Integration-Id": "vscode-chat"}

and calling the endpoint, I get

400 Github_copilotException - model gpt-5.1-codex is not accessible via the /chat/completions endpoint.

I tried adding wire_api: responses or model: github_copilot/responses/gpt-5.1-codex

but both then lead to 500 internal errors:

Github_copilotException - functools.partial() got multiple values for keyword argument 'acompletion'

Relevant log output

litellm-1   | 12:54:59 - LiteLLM Proxy:ERROR: common_request_processing.py:707 - litellm.proxy.proxy_server._handle_llm_api_exception(): Exception occured - litellm.APIConnectionError: APIConnectionError: Github_copilotException - functools.partial() got multiple values for keyword argument 'acompletion'. Received Model Group=copilot-gpt-5.1-codex
litellm-1   | Available Model Group Fallbacks=None LiteLLM Retried: 1 times, LiteLLM Max Retries: 2
litellm-1   | Traceback (most recent call last):
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/main.py", line 584, in acompletion
litellm-1   |     func = partial(completion, **completion_kwargs, **kwargs)
litellm-1   | TypeError: functools.partial() got multiple values for keyword argument 'acompletion'
litellm-1   | 
litellm-1   | During handling of the above exception, another exception occurred:
litellm-1   | 
litellm-1   | Traceback (most recent call last):
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/proxy/proxy_server.py", line 4782, in chat_completion
litellm-1   |     result = await base_llm_response_processor.base_process_llm_request(
litellm-1   |              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
litellm-1   |     ...<16 lines>...
litellm-1   |     )
litellm-1   |     ^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/proxy/common_request_processing.py", line 502, in base_process_llm_request
litellm-1   |     responses = await llm_responses
litellm-1   |                 ^^^^^^^^^^^^^^^^^^^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/router.py", line 1093, in acompletion
litellm-1   |     raise e
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/router.py", line 1069, in acompletion
litellm-1   |     response = await self.async_function_with_fallbacks(**kwargs)
litellm-1   |                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/router.py", line 4037, in async_function_with_fallbacks
litellm-1   |     return await self.async_function_with_fallbacks_common_utils(
litellm-1   |            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
litellm-1   |     ...<8 lines>...
litellm-1   |     )
litellm-1   |     ^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/router.py", line 3995, in async_function_with_fallbacks_common_utils
litellm-1   |     raise original_exception
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/router.py", line 4029, in async_function_with_fallbacks
litellm-1   |     response = await self.async_function_with_retries(*args, **kwargs)
litellm-1   |                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/router.py", line 4234, in async_function_with_retries
litellm-1   |     raise original_exception
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/router.py", line 4125, in async_function_with_retries
litellm-1   |     response = await self.make_call(original_function, *args, **kwargs)
litellm-1   |                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/router.py", line 4245, in make_call
litellm-1   |     response = await response
litellm-1   |                ^^^^^^^^^^^^^^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/router.py", line 1372, in _acompletion
litellm-1   |     raise e
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/router.py", line 1324, in _acompletion
litellm-1   |     response = await _response
litellm-1   |                ^^^^^^^^^^^^^^^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/utils.py", line 1638, in wrapper_async
litellm-1   |     raise e
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/utils.py", line 1484, in wrapper_async
litellm-1   |     result = await original_function(*args, **kwargs)
litellm-1   |              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/main.py", line 617, in acompletion
litellm-1   |     raise exception_type(
litellm-1   |     ...<5 lines>...
litellm-1   |     )
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/main.py", line 598, in acompletion
litellm-1   |     response = await init_response
litellm-1   |                ^^^^^^^^^^^^^^^^^^^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/completion_extras/litellm_responses_transformation/handler.py", line 173, in acompletion
litellm-1   |     result = await aresponses(
litellm-1   |              ^^^^^^^^^^^^^^^^^
litellm-1   |     ...<2 lines>...
litellm-1   |     )
litellm-1   |     ^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/utils.py", line 1638, in wrapper_async
litellm-1   |     raise e
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/utils.py", line 1484, in wrapper_async
litellm-1   |     result = await original_function(*args, **kwargs)
litellm-1   |              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/responses/main.py", line 458, in aresponses
litellm-1   |     raise litellm.exception_type(
litellm-1   |     ...<5 lines>...
litellm-1   |     )
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/responses/main.py", line 439, in aresponses
litellm-1   |     response = await init_response
litellm-1   |                ^^^^^^^^^^^^^^^^^^^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/responses/litellm_completion_transformation/handler.py", line 117, in async_response_api_handler
litellm-1   |     ] = await litellm.acompletion(
litellm-1   |         ^^^^^^^^^^^^^^^^^^^^^^^^^^
litellm-1   |         **acompletion_args,
litellm-1   |         ^^^^^^^^^^^^^^^^^^^
litellm-1   |     )
litellm-1   |     ^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/utils.py", line 1638, in wrapper_async
litellm-1   |     raise e
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/utils.py", line 1484, in wrapper_async
litellm-1   |     result = await original_function(*args, **kwargs)
litellm-1   |              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/main.py", line 617, in acompletion
litellm-1   |     raise exception_type(
litellm-1   |           ~~~~~~~~~~~~~~^
litellm-1   |         model=model,
litellm-1   |         ^^^^^^^^^^^^
litellm-1   |     ...<3 lines>...
litellm-1   |         extra_kwargs=kwargs,
litellm-1   |         ^^^^^^^^^^^^^^^^^^^^
litellm-1   |     )
litellm-1   |     ^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 2328, in exception_type
litellm-1   |     raise e  # it's already mapped
litellm-1   |     ^^^^^^^
litellm-1   |   File "/usr/lib/python3.13/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 569, in exception_type
litellm-1   |     raise APIConnectionError(
litellm-1   |     ...<7 lines>...
litellm-1   |     )
litellm-1   | litellm.exceptions.APIConnectionError: litellm.APIConnectionError: APIConnectionError: Github_copilotException - functools.partial() got multiple values for keyword argument 'acompletion'. Received Model Group=copilot-gpt-5.1-codex
litellm-1   | Available Model Group Fallbacks=None LiteLLM Retried: 1 times, LiteLLM Max Retries: 2
litellm-1   | INFO:     172.29.0.5:46852 - "POST /v1/chat/completions HTTP/1.1" 500 Internal Server Error

Are you a ML Ops Team?

No

What LiteLLM version are you on ?

v1.79.3-stable

Twitter / LinkedIn details

No response

[nbsp1221]

I've analyzed this further and reproduced the issue on the latest main branch.

It appears that the gpt-5.1-codex model from Copilot strictly requires the /responses endpoint and does not support /chat/completions.

However, after looking into the current LiteLLM logic, it seems implemented primarily for standard chat completions. Since the model relies on a different endpoint structure (/responses), this looks like it requires a new implementation to support that endpoint properly, rather than just a simple fix.

[nbsp1221]

I've opened a PR (#16845) to address this.

Based on the analysis, I used AI to help fast-track the implementation of the /responses endpoint logic. It seems to fix the issue in my local tests, but I'd appreciate a review to ensure it meets the project's standards. Hope this helps!

[msexxeta]

nice, your PR only mentions gpt-5.1-codex, will this also work for gpt-5-codex?

[nbsp1221]

nice, your PR only mentions gpt-5.1-codex, will this also work for gpt-5-codex?

Yes, it works with the /v1/responses/ endpoint just like gpt-5.1-codex model.

model_list:
  - model_name: github_copilot/gpt-5-codex
    model_info:
      mode: responses
    litellm_params:
      model: github_copilot/gpt-5-codex
      extra_headers:
        editor-version: "vscode/1.95.0"
        editor-plugin-version: "copilot-chat/0.26.7"