What this error means
API Error: 400 litellm bad request — Claude Code multi-turn conversation hangs via LiteLLM gateway is a LiteLLM failure pattern reported for developers trying to fix claude code getting stuck/hanging during multi-turn conversations when routed through litellm gateway. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.
Why this happens
LiteLLM issue #27839 reports Claude Code hanging during multi-turn conversations when routed through LiteLLM gateway. Error: API Error: 400 with litellm bad request message. Affects Chinese developer community using proxy setups.
Common causes
- Developers using Claude Code with LiteLLM as a proxy experience multi-turn conversations that hang with a 400 bad request error. This breaks the core coding workflow and wastes paid API credits.
- LiteLLM issue #27839 reports Claude Code hanging during multi-turn conversations when routed through LiteLLM gateway. Error: API Error: 400 with litellm bad request message. Affects Chinese developer community using proxy setups.
Quick fixes
- Confirm the exact error signature matches
API Error: 400 litellm bad request — Claude Code multi-turn conversation hangs via LiteLLM gateway. - Check the LiteLLM account, local tool state, and provider configuration involved in the failing workflow.
- 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
- Capture the exact error message and the command, editor action, or request that triggered it.
- Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
- Review the source evidence below and compare it with your environment.
- Apply one change at a time and rerun the smallest failing action.
- 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.