[Bug]: Invalid model name passed in model=None

[habitoti]

What happened?

I installed the LLMLite proxy to map OpenAI (from paperless-gpt) calls to my Azure instance. However it seems that the configured model doesn't make it into the call:

16:39:17 - LiteLLM Proxy:DEBUG: common_request_processing.py:307 - An error occurred: 400: {'error': '/chat/completions: Invalid model name passed in model=None. Call `/v1/models` to view available models for your key.'} 

The configuration was finished with the proper model:

I wouldn't be surprised if this is a configuration error on my side, however after double- and triple checking and looking through the few available logs I just have no clue what else to check or do.

My config for the Docker install was this:

 "model_list": [
        {
            "model_name": "gpt-4o-mini",
            "litellm_params": {
                "model": "azure/gpt-4o-mini",
                "api_base": "os.environ/AZURE_API_BASE",
                "api_key": "os.environ/AZURE_API_KEY",
                "api_version": "2025-01-01-preview"
            }
        }
    ]

Relevant log output

16:39:17 - LiteLLM:DEBUG: litellm_logging.py:412 - self.optional_params: {}
16:39:17 - LiteLLM Proxy:ERROR: common_request_processing.py:298 - litellm.proxy.proxy_server._handle_llm_api_exception(): Exception occured - 400: {'error': '/chat/completions: Invalid model name passed in model=None. Call `/v1/models` to view available models for your key.'}
Traceback (most recent call last):
  File "/usr/lib/python3.13/site-packages/litellm/proxy/proxy_server.py", line 3552, in chat_completion
    return await base_llm_response_processor.base_process_llm_request(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    ...<16 lines>...
    )
    ^
  File "/usr/lib/python3.13/site-packages/litellm/proxy/common_request_processing.py", line 197, in base_process_llm_request
    llm_call = await route_request(
               ^^^^^^^^^^^^^^^^^^^^
    ...<4 lines>...
    )
    ^
  File "/usr/lib/python3.13/site-packages/litellm/proxy/route_llm_request.py", line 113, in route_request
    raise ProxyModelNotFoundError(
    ...<2 lines>...
    )
litellm.proxy.route_llm_request.ProxyModelNotFoundError: 400: {'error': '/chat/completions: Invalid model name passed in model=None. Call `/v1/models` to view available models for your key.'}

Are you a ML Ops Team?

No

What LiteLLM version are you on ?

1.65.0

Twitter / LinkedIn details

No response

[ishaan-jaff]

try a basic curl and validate that works. I suspect the issue is on your client side request

[habitoti]

It was a test curl that actually didn't work and yielded the above error.
Ultimately I just configured the proxy for a test in the environment where I need it (paperless-gpt), and there it works now...

This was the curl:

curl --location --request POST 'localhost:4000/v1/chat/completions' \
-H 'Authorization: Bearer <redacted>' \
-H 'Content-Type: application/json' \
-d '{
    "max_tokens": 1000,
    "model": "gpt-4o-mini”,
    "temperature": 0.8,
    "top_p": 1,
    "presence_penalty": 1,
    "messages": [
        {
            "role": "user",
            "content": "Hello"
        }
    ],
    "stream": true
}'

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.