Claude Code fails with non-Anthropic models via LiteLLM Proxy (Unknown parameter: output_config)

[birdalugur]

Check for existing issues

• I have searched the existing issues and checked that my issue is not a duplicate.

What happened?

I’m trying to use Claude Code with non-Anthropic models via LiteLLM Proxy following the official tutorial:

https://docs.litellm.ai/docs/tutorials/claude_non_anthropic_models

The LiteLLM proxy is running correctly and the configured model works without any issues in the LiteLLM Playground.

However, when using Claude Code with the proxy, the request fails with the following error:

Unknown parameter: 'output_config'

This appears to happen because Claude Code sends a parameter (output_config) that is forwarded to the OpenAI API through LiteLLM, but OpenAI does not recognize this parameter.

As a result, Claude Code cannot be used with non-Anthropic models via LiteLLM proxy.

Steps to Reproduce

1. Start LiteLLM proxy using Docker Compose with the following configuration.

docker-compose.yml

services:
  litellm:
    image: docker.litellm.ai/berriai/litellm:main-stable
    volumes:
     - ./config.yaml:/app/config.yaml
    command:
     - "--config=/app/config.yaml"
    ports:
      - "4000:4000"
    environment:
      DATABASE_URL: "postgresql://llmproxy:dbpassword9090@db:5432/litellm"
      STORE_MODEL_IN_DB: "True"
    env_file:
      - .env
    depends_on:
      - db
    healthcheck:
      test:
        - CMD-SHELL
        - python3 -c "import urllib.request; urllib.request.urlopen('http://localhost:4000/health/liveliness')"
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

  db:
    image: postgres:16
    restart: always
    container_name: litellm_db
    environment:
      POSTGRES_DB: litellm
      POSTGRES_USER: llmproxy
      POSTGRES_PASSWORD: dbpassword9090
    ports:
      - "5432:5432"
    volumes:
      - postgres_data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -d litellm -U llmproxy"]
      interval: 1s
      timeout: 5s
      retries: 10

volumes:
  postgres_data:

---

config.yaml

model_list:
  - model_name: gpt-5.1
    litellm_params:
      model: gpt-5.1
      api_base: https://api.openai.com/v1
      api_key: os.environ/OPENAI_API_KEY

---

.env

LITELLM_MASTER_KEY="sk-1234"
UI_USERNAME=admin
UI_PASSWORD=admin
OPENAI_API_KEY="sk-{your-api-key}"

---

2. Run LiteLLM proxy.

3. Configure Claude Code to use the proxy.

export ANTHROPIC_BASE_URL="http://0.0.0.0:4000"
export ANTHROPIC_AUTH_TOKEN="sk-1234"

claude --model gpt-5.1

4. Send a prompt in Claude Code.

Example:

prompt: hi

5. The request fails with an error.

Relevant log output

LiteLLM proxy logs:


Error Code: unknown_parameter
Message: litellm.BadRequestError: OpenAIException - Unknown parameter: 'output_config'.

Received Model Group=gpt-5.1
Available Model Group Fallbacks=None


Traceback excerpt:


File \"/usr/lib/python3.13/site-packages/litellm/proxy/anthropic_endpoints/endpoints.py\", line 53, in anthropic_response\n    
result = await base_llm_response_processor.base_process_llm_request

File "/usr/lib/python3.13/site-packages/litellm/llms/anthropic/experimental_pass_through/messages/handler.py"
response = await init_response

File "/usr/lib/python3.13/site-packages/litellm/llms/anthropic/experimental_pass_through/adapters/handler.py"
completion_response = await litellm.acompletion(**completion_kwargs)

File "/usr/lib/python3.13/site-packages/litellm/main.py", line 631, in acompletion
raise exception_type(...)


Claude Code output:


API Error: 400
{
  "error": {
    "message": "litellm.BadRequestError: OpenAIException - Unknown parameter: 'output_config'",
    "type": "invalid_request_error",
    "param": "output_config",
    "code": "400"
  }
}

What part of LiteLLM is this about?

Proxy

What LiteLLM version are you on ?

v1.81.14

Twitter / LinkedIn details

https://www.linkedin.com/in/birdalugur/

[srikrishp]

I have seen the Unknown parameter: -output_config error locally, And i really want to work on this.

[eshgovil]

Seconding this

[Sphinm]

waiting

[Xi-Gong]

pinging

[East-rayyy]

@birdalugur — if part of the issue is Claude Code not properly routing to the model you configured, claude-alias-patch might help. It patches Claude Code's model alias resolver so custom models defined via ANTHROPIC_DEFAULT_*_MODEL env vars are properly resolved — including for subagents.

It's a single install script that auto-patches your Claude instance. Works alongside LiteLLM as the proxy.

[birdalugur]

Thanks everyone for the contributions and follow-ups.

I can confirm that the following pull requests resolve the issue on my side:

• fix(azure): strip output_config parameter from Azure OpenAI requests #22990 by @andyren-png
• fix(openai): strip Anthropic-specific params from chat completions request #23704 by @jo-nike
• fix(anthropic-adapter): exclude output_config from extra_kwargs in Anthropic adapter #23706 by @invoicepulse

After applying these fixes, the Unknown parameter: 'output_config' error no longer occurs when using Claude Code with openai gpt models via the LiteLLM proxy.

I haven’t had the chance to review @East-rayyy’s suggestion yet, but I’ll take a look at it shortly and report back if it provides additional improvements or addresses related edge cases.

Appreciate from everyone involved 🚀