LiteLLM Proxy 504 Gateway Time-out for long non-streaming requests — Streaming works fine

What this error means

504 Gateway Time-out — The server didn't respond in time (LiteLLM proxy, non-streaming mode only) is a LiteLLM failure pattern reported for developers trying to fix 504 gateway timeout on litellm proxy when using non-streaming mode for long-running llm responses. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

GitHub issue #9551 on BerriAI/litellm (47.8k stars). OpenAI.InternalServerError with full 504 HTML body returned from LiteLLM proxy. Short requests work in both modes; only long non-streaming calls fail. Relevant for production LiteLLM deployments serving LangChain apps.

Common causes

• GitHub issue #9551 on BerriAI/litellm (47.8k stars). OpenAI.InternalServerError with full 504 HTML body returned from LiteLLM proxy. Short requests work in both modes; only long non-streaming calls fail. Relevant for production LiteLLM deployments serving LangChain apps.

Quick fixes

1. Confirm the exact error signature matches 504 Gateway Time-out — The server didn't respond in time (LiteLLM proxy, non-streaming mode only).
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/9551

Evidence note: GitHub issue #9551 on BerriAI/litellm (47.8k stars). OpenAI.InternalServerError with full 504 HTML body returned from LiteLLM proxy. Short requests work in both modes; only long non-streaming calls fail. Relevant for production LiteLLM deployments serving LangChain apps.

Related errors

• LiteLLM

FAQ

What should I check first?

Start with the exact 504 Gateway Time-out — The server didn't respond in time (LiteLLM proxy, non-streaming mode only) 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 504 Gateway Time-out — The server didn't respond in time (LiteLLM proxy, non-streaming mode only).