What this error means

model_settings thinking=False silently dropped — reasoning field missing from OpenRouter request body is a OpenRouter failure pattern reported for developers trying to fix pydantic ai silently dropping thinking=false setting when routing through openrouter, xai, or bedrock reasoning models. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

Pydantic AI issue #5379 (created 2026-05-12, 3 comments). thinking=False silently dropped for reasoning models routed through OpenRouterModel, xAI, Bedrock. HTTP body contains no reasoning field. No exception or warning thrown — completely silent failure.

Common causes

  • Pydantic AI developers set model_settings={'thinking': False} to disable reasoning mode, but the setting is silently dropped — no exception, no warning. The HTTP body sent to OpenRouter contains no reasoning field at all. Affects cost control and response behavior for paid API usage
  • Pydantic AI issue #5379 (created 2026-05-12, 3 comments). thinking=False silently dropped for reasoning models routed through OpenRouterModel, xAI, Bedrock. HTTP body contains no reasoning field. No exception or warning thrown — completely silent failure.

Quick fixes

  1. Confirm the exact error signature matches model_settings thinking=False silently dropped — reasoning field missing from OpenRouter request body.
  2. Check the OpenRouter 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.