What this error means

400 Bad Request - tool_choice named function format is a LiteLLM failure pattern reported for developers trying to fix litellm 400 error when using tool_choice named function format with gpt-5.4/5.5 models. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

GitHub issue #27611 in BerriAI/litellm. Affects all GPT-5.4 and GPT-5.5 models through LiteLLM's Chat Completions → Responses API bridge.

Common causes

  • Calling GPT-5.4 or GPT-5.5 through LiteLLM's Chat Completions endpoint with named tool_choice (type: function, function: {name: ...}) causes a 400 error because LiteLLM's bridge to the Responses API passes the parameter incorrectly.
  • GitHub issue #27611 in BerriAI/litellm. Affects all GPT-5.4 and GPT-5.5 models through LiteLLM's Chat Completions → Responses API bridge.

Quick fixes

  1. Confirm the exact error signature matches 400 Bad Request - tool_choice named function format.
  2. Check the LiteLLM account, local tool state, and provider configuration involved in the failing workflow.
  3. Compare the failing environment with a known working setup, then change one configuration value at a time.

Platform/tool-specific checks

  • Verify the command, editor, extension, or API client that produced the error.
  • Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
  • Avoid deleting credentials, local model data, or project settings until the failing scope is clear.

Step-by-step troubleshooting

  1. Capture the exact error message and the command, editor action, or request that triggered it.
  2. Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
  3. Review the source evidence below and compare it with your environment.
  4. Apply one change at a time and rerun the smallest failing action.
  5. Keep the working fix documented for the team or deployment environment.

How to prevent it

  • Keep provider/tool configuration documented.
  • Record non-secret diagnostics such as tool version, provider name, model name, and command path.
  • Add a lightweight check before CI or production workflows depend on the tool.