# AI Gateway — API Docs

> Public API documentation for the free-ai OpenAI-compatible LLM gateway.

## Docs

- [Analytics](https://ai-gateway.sassmaker.com/docs/analytics): Retrieve aggregated usage statistics for a specific project — request counts, success/failure rates, and breakdowns by provider and model.
- [Authentication](https://ai-gateway.sassmaker.com/docs/authentication): How to obtain and use API keys with the AI Gateway.
- [Chat Completions](https://ai-gateway.sassmaker.com/docs/chat-completions): Generate chat completions using the OpenAI-compatible /v1/chat/completions endpoint.
- [Decision APIs](https://ai-gateway.sassmaker.com/docs/decisions): Typed decisions and comparisons over one frozen input.
- [Embeddings](https://ai-gateway.sassmaker.com/docs/embeddings): Generate vector embeddings using /v1/embeddings, including the Modal EmbeddingGemma 2 experiment.
- [Error Handling](https://ai-gateway.sassmaker.com/docs/error-handling): Understand the gateway's error response format, error types, HTTP status codes, and how to identify requests using gateway headers.
- [Getting Started](https://ai-gateway.sassmaker.com/docs/getting-started): An OpenAI-compatible AI gateway that routes requests across free-tier providers with health-aware routing, streaming, and analytics.
- [Health](https://ai-gateway.sassmaker.com/docs/health): Check the real-time health state of every model in the gateway, including success rates, average latency, cooldown status, and daily usage.
- [Image Generation](https://ai-gateway.sassmaker.com/docs/images): Generate images using the OpenAI-compatible /v1/images/generations endpoint, routed across Together FLUX, Workers AI, Pollinations, NVIDIA NIM, and Gemini Imagen.
- [Live Dashboard](https://ai-gateway.sassmaker.com/docs/dashboard): Public HTML dashboard at /dashboard showing real-time KPIs, throttle heatmap, model health, and project usage for the gateway.
- [Models](https://ai-gateway.sassmaker.com/docs/models): List available models and their metadata using GET /v1/models.
- [Provider Stats](https://ai-gateway.sassmaker.com/docs/provider-stats): Real-time throttle, success, and cooldown telemetry per provider via GET /v1/stats/providers — the raw signal behind the gateway's health-aware routing.
- [Rate Limiting](https://ai-gateway.sassmaker.com/docs/rate-limiting): Learn how the gateway enforces IP-based and per-provider rate limits, and how to handle 429 responses gracefully in your application.
- [Responses API](https://ai-gateway.sassmaker.com/docs/responses-api): Generate responses using the OpenAI Responses API format via /v1/responses.
- [Speech-to-Speech](https://ai-gateway.sassmaker.com/docs/speech-to-speech): Send audio input and receive audio output via the /v1/audio/speech-to-speech endpoint.
- [Speech-to-Text](https://ai-gateway.sassmaker.com/docs/speech-to-text): Transcribe audio files to text using the OpenAI-compatible /v1/audio/transcriptions endpoint.
- [Text-to-Speech](https://ai-gateway.sassmaker.com/docs/text-to-speech): Synthesize audio from text via the OpenAI-compatible /v1/audio/speech endpoint, backed by Cloudflare Workers AI MeloTTS.
- [Video Generation](https://ai-gateway.sassmaker.com/docs/videos): Submit async video generation jobs via /v1/videos/generations and poll for completion. Routed through Together AI to Sora, Veo, Kling, Wan, Seedream, and Vidu.