Logo
Deploy Now

Categories

Self-Hosted Developer Tools AI LLM API Gateway Proxy OpenAI Compatible

Stars

19,357

Forks

2,825

Watchers

89

Developer links

Last Updated: 08-22-2026 03:45 PM (UTC)

FreeLLMAPI

FreeLLMAPI collapses the chaos of 29 free LLM providers — Google AI, Cerebras, Groq, Mistral, OpenRouter, GitHub Models, Cohere, Cloudflare Workers AI, NVIDIA NIM, HuggingFace, SiliconFlow, Reka, Z.ai, and more — into a single /v1 endpoint that speaks both OpenAI and Anthropic protocols. The smart router selects the best available model for each request, automatically fails over to the next provider when rate limits hit, and tracks per-key token consumption so you never exceed a free-tier cap. Keys are stored with AES-256-GCM encryption and clients authenticate using a single unified bearer token, never exposing upstream provider credentials to downstream applications. The catalog tracks 251 model families across 358 provider/model endpoints with approximately 4 billion tokens per month of aggregate free-tier capacity, auto-refreshing from a signed manifest at freellmapi.co twice daily without requiring git pulls. Beyond chat completions, the proxy handles embedding, image generation, and audio/TTS endpoints, plus structured outputs with JSON schema forwarding, JSON healing, and format-ignore failover. An integrated MCP server at /mcp provides gateway introspection for coding agents, while the self-hosted OpenAPI reference at /v1/docs documents every route. Compatible with OpenAI SDKs, LangChain, LlamaIndex, Continue, Claude Code, and Hermes — just change base_url. Deploy via Docker, npm, or build from source. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

FreeLLMAPI
FreeLLMAPI
FreeLLMAPI
FreeLLMAPI
FreeLLMAPI

Benefits

  • 4 Billion Free Tokens Monthly
  • Aggregates free-tier quotas from 29 providers into one pool with automatic failover, delivering approximately 4 billion tokens per month across 358 model endpoints without cost.
  • Single Unified Bearer Token
  • Clients authenticate with one freellmapi token while upstream provider keys remain encrypted with AES-256-GCM on the server, never exposed to downstream applications or scripts.
  • Auto-Refreshing Model Catalog
  • A signed manifest from freellmapi.co updates available providers, models, and quotas twice daily without manual intervention, tracking launches, retirements, and quota changes automatically.
  • Drop-In OpenAI Compatibility
  • Works with any OpenAI-compatible client library by changing base_url — supports LangChain, LlamaIndex, Continue, Claude Code, Hermes, and standard OpenAI Python/Node SDKs.

Features

  • Smart Routing Engine
  • Selects the best available model per request based on configured preferences and automatically fails over to alternate providers when rate limits or errors are encountered.
  • Multi-Modal Endpoints
  • Serves chat completions, embeddings, image generation, and audio/TTS through the same /v1 API surface with provider-transparent routing across all supported modalities.
  • Anthropic-Compatible API
  • Exposes /v1/messages endpoint compatible with Anthropic SDKs and Claude Code, including system-role handling and thought-signature preservation for seamless integration.
  • MCP Gateway Server
  • Built-in Model Context Protocol server at /mcp provides gateway introspection for coding agents, exposing available models and routing capabilities programmatically.
  • Management Dashboard
  • Web-based admin interface for managing provider keys, monitoring per-key usage, browsing the model catalog, and configuring routing preferences and failover policies.