Error category
Fix LiteLLM proxy, gateway, virtual key, provider routing, budget, schema validation, and OpenAI-compatible API errors.
This LiteLLM troubleshooting hub collects real error signatures, quick fixes, common causes, and step-by-step debugging paths for developers who need a practical answer instead of a broad overview.
266 crawlable articles in this category. 124 additional records are indexed in JSON only (no standalone HTML route).
Browse LiteLLM records in the data catalog — search JSON index entries, including data-only records without standalone HTML guides.
Start by matching the exact error message, then check the technology, environment, credentials, network path, and deployment context. The pages below are grouped so you can move from broad LiteLLM symptoms to specific root-cause families without relying on client-side search.
Evidence labels are derived at build time from each Markdown record. Source-backed entries have public URLs under a Sources checked section, while partial-source entries expose public links without a complete source block.
These entries include public source URLs in the imported page body. Use them first when you need evidence for provider behavior, SDK regressions, or version-specific failures.
Fix LiteLLM proxy ConnectionRefusedError by verifying proxy process is running on expected host:port, resolving Docker network isolation, unsetting conflicting LITELLM_PORT env variable Includes evidence for LiteLLM troubleshooting demand.
litellm.llms.custom_httpx.http_handler.HTTPHandler.post: Connection refused OR httpx.ConnectError: [Errno 111] Connection refused After upgrading to LiteLLM 1.82.1, previously working OpenRouter model IDs throw 404 errors. Users proxying through LiteLLM proxy lose access to OpenRouter models and need quick workaround to restore routing to healthy deployments. Includes evidence for LiteLLM troubleshooting demand.
litellm.CallFailed: Error code: 404 — OpenRouter model IDs stopped working after LiteLLM upgrade to v1.82.1 Debug LiteLLM proxy when routed API calls time out or models become unavailable across integrated providers (OpenAI, Anthropic, local models) Includes evidence for LiteLLM troubleshooting demand.
LiteLLM proxy timeout — model unreachable or provider timeout on multi-provider routing fallback Understand and mitigate LiteLLM Proxy auth bypass via SQL injection where DB connection errors grant PROXY_ADMIN privileges without valid keys Includes evidence for LiteLLM troubleshooting demand.
Authentication failed / failed-to-connect-to-db / PrismaError pool timeout connection error Determine if a project installed compromised LiteLLM versions and clean the installation; scan GitLab CI/CD jobs and GitHub Actions for affected deployments Includes evidence for LiteLLM troubleshooting demand.
LiteLLM package compromised — versions 1.82.7 and 1.82.8 contain malicious code contacting external C2 domains Developer running LiteLLM proxy gets RouterRateLimitErrorBasic with 'No deployments available for selected model' when calling /chat/completions. Proxy returns 429 and crashes with visible traceback. Needs config fix to resolve deployment routing. Includes evidence for LiteLLM troubleshooting demand.
litellm.types.router.RouterRateLimitErrorBasic: No deployments available for selected model. — 429 response from LiteLLM proxy with full stack trace Fix LiteLLM proxy failing downstream calls to VertexAI/Gemini models with 429 RESOURCE_EXHAUSTED errors, including proper retry and routing configuration for multi-provider setups. Includes evidence for LiteLLM troubleshooting demand.
litellm.RateLimitError: VertexAIException - RESOURCE_EXHAUSTED Fix LiteLLM proxy logging rate limit errors as deployment failures; understand why stack trace prints 3x even with num_retries: 0 Includes evidence for LiteLLM troubleshooting demand.
litellm.RateLimitError: VertexAIException - {"error": {"code": 429, "message": "Resource has been exhausted (e.g. check quota).", "status": "RESOURCE_EXHAUSTED"}} — logged as 'No deployments available for selected model' Fix LiteLLM proxy memory leak / state corruption bug where configured models disappear from routing pool after prolonged operation without database backend Includes evidence for LiteLLM troubleshooting demand.
Proxy silently drops all models after extended runtime (config-only, no DB) — all LLM API calls start returning Not Fund Error despite valid configuration Fix OpenRouter rate limit failover behavior where model switch breaks completely after hitting $5 free tier spending cap Includes evidence for OpenRouter troubleshooting demand.
After hitting OpenRouter API rate limit ($5 spending cap), switching models fails with 'model not allowed' error for ALL models even after limit resets Fix token acquisition failure when setting up GitHub Copilot as a backend model in LiteLLM proxy Includes evidence for LiteLLM troubleshooting demand.
Error polling for access token when configuring github copilot model Fix LiteLLM proxy /v1/models endpoint so wildcard team BYOK routes properly expand and discover models stored under litellm_credential_name Includes evidence for LiteLLM troubleshooting demand.
/v1/models wildcard expansion fails to find team-scoped wildcard deployment models; team.models = ['openai/*'] does not resolve correctly when check_provider_endpoint=true Detect when LiteLLM proxy routes requests to models it doesn't recognize pricing for — silent zero-cost masking real token costs impacts billing accuracy Includes evidence for LiteLLM troubleshooting demand.
cost_per_token() in cost_calculator.py returns (0.0, 0.0) instead of raising error for unknown/unrecognized models Fix LiteLLM proxy returning spurious 'guardrails feature unavailable' error messages when guardrails integration was never set up, confusing production deployments Includes evidence for LiteLLM troubleshooting demand.
False-positive guardrails feature unavailable error when guardrails are not configured in LiteLLM Teams running LiteLLM proxy encounter 401 Unauthorized errors due to Pydantic v2 Optional field handling changes where missing default values break team membership validation. Includes evidence for LiteLLM troubleshooting demand.
LiteLLM_TeamMembership.litellm_budget_table missing default causes ValidationError → 401 response Stop false positive rate_limit classification when OpenAPI rejects unknown parameters containing rate_limit in their names; fix exception mapping in LiteLLM proxy Includes evidence for LiteLLM troubleshooting demand.
OpenAI's Unknown parameter 400 errors get misclassified as 429 RateLimitError when the rejected field name contains 'rate_limit' substring (e.g., _litellm_rate_limit_descriptors) Developer running LiteLLM proxy encounters broken UI features, incomplete functionality after proxy upgrade, affecting monitoring and debugging capabilities Includes evidence for LiteLLM troubleshooting demand.
LiteLLM proxy UI and features broken/incomplete over success Fix LiteLLM Responses API bridge dropping nested function tool names and forwarding Responses-only tool types that downstream providers (DeepSeek, GLM, MiniMax) reject Includes evidence for LiteLLM troubleshooting demand.
Responses bridge: normalize function tools and drop unsupported tool types — Invalid 'tools[0].function.name': empty string; tools[0].type: unknown variant 'custom' Fix LiteLLM Response API bridge passing Chat Completions-style chatcmpl-* IDs as message item IDs into native OpenAI Responses endpoint, causing OpenAI to reject the request Includes evidence for LiteLLM troubleshooting demand.
Invalid 'input[1].id': 'chatcmpl-dfa2da3a-1586-4ff7-b64e-f59c692a5d11'. Expected an ID that begins with 'msg' Fix LiteLLM proxy Prisma migration failure when running in non-root Docker container on Alpine/Wolfi-based images Includes evidence for LiteLLM troubleshooting demand.
Prisma migrations not applied with docker non_root image — Prisma warning: doesn't know which engines to download for Linux distro wolfi, falling back to debian builds Continue through the full static archive for this hub. Every listed page is crawlable and keeps its existing canonical URL.