What this error means
litellm.llms.custom_httpx.http_handler.HTTPHandler.post: Connection refused OR httpx.ConnectError: [Errno 111] Connection refused is a LiteLLM failure pattern reported for developers trying to fix litellm proxy connectionrefusederror by verifying proxy process is running on expected host:port, resolving docker network isolation, unsetting conflicting litellm_port env variable. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.
Why this happens
Markaicode article (June 2026) documents that ConnectionRefusedError accounts for ~40% of all LiteLLM startup errors. Root causes are port mismatch, wrong host inside Docker (localhost vs host.docker.internal), and firewall/SELinux blocking port 4000. GitHub issue #27823 notes RouterRateLimitError masking underlying quota errors without Retry-After header. Category mapping: LiteLLM → LiteLLM.
Common causes
- Markaicode article (June 2026) documents that ConnectionRefusedError accounts for ~40% of all LiteLLM startup errors. Root causes are port mismatch, wrong host inside Docker (localhost vs host.docker.internal), and firewall/SELinux blocking port 4000. GitHub issue #27823 notes RouterRateLimitError masking underlying quota errors without Retry-After header. Category mapping: LiteLLM → LiteLLM.
Quick fixes
- Confirm the exact error signature matches
litellm.llms.custom_httpx.http_handler.HTTPHandler.post: Connection refused OR httpx.ConnectError: [Errno 111] Connection refused. - Check the LiteLLM account, local tool state, and provider configuration involved in the failing workflow.
- Confirm the local service is running on the expected host and port, then retry the smallest request.
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.