LiteLLM structured output (JSON schema) fails for Anthropic models on Bedrock Converse API

What this error means

LiteLLM Structured Output fails for Anthropic models on bedrock/converse: Extra inputs are not permitted is a LiteLLM failure pattern reported for developers trying to fix litellm structured output not working with anthropic models on bedrock converse api. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

Works on Converse API for Nova models and Invoke API for both. Fails only on Converse API for Anthropic models. Bedrock rejects output_config.format field.

Common causes

• BedrockException: output_config.format: Extra inputs not permitted when using responses API with Anthropic models on Bedrock Converse
• Works on Converse API for Nova models and Invoke API for both. Fails only on Converse API for Anthropic models. Bedrock rejects output_config.format field.

Quick fixes

1. Confirm the exact error signature matches LiteLLM Structured Output fails for Anthropic models on bedrock/converse: Extra inputs are not permitted.
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.

Sources checked

• https://github.com/BerriAI/litellm/issues/27846

Evidence note: Works on Converse API for Nova models and Invoke API for both. Fails only on Converse API for Anthropic models. Bedrock rejects output_config.format field.

Related errors

• LiteLLM Vertex AI URL wrong
• Claude Code Bedrock beta flag 400

FAQ

What should I check first?

Start with the exact LiteLLM Structured Output fails for Anthropic models on bedrock/converse: Extra inputs are not permitted text and the smallest action that reproduces it.

Can I ignore this error?

No. Treat it as a failed LiteLLM workflow until the root cause is understood.

Is this guaranteed to have one fix?

No. The imported evidence supports the troubleshooting path above, but tool behavior can vary by account, plan, version, provider, and local configuration.

How do I know the fix worked?

Rerun the same command, editor action, or request. The fix is working when that action completes without LiteLLM Structured Output fails for Anthropic models on bedrock/converse: Extra inputs are not permitted.