sass-maker module

AI Gateway

OpenAI-compatible routing across free-tier AI providers. Health-aware selection, streaming, embeddings, and built-in analytics.

View Docs Dashboard Health Status

🔀

Multi-Provider Routing

Automatically routes to Workers AI, Groq, Gemini, OpenRouter, and Cerebras. Round-robin with health-aware fallback.

🏥

Health-Aware Selection

Tracks success rates, latency, and cooldowns per model. Unhealthy providers are automatically skipped.

⚡

Streaming Support

Full SSE streaming for chat completions and responses API. Compatible with OpenAI SDK stream handling.

📊

Embeddings

Generate embeddings via Workers AI, Gemini, or Voyage AI. Standard OpenAI embeddings format.

📈

Built-in Analytics

Request logging, per-provider stats, and a usage dashboard. Monitor everything from /v1/analytics.

🔒

Rate Limiting

IP-based rate limiting on public endpoints. Per-provider daily limits with configurable thresholds.

Quick Start

 # Chat completion

curl https://your-gateway.workers.dev/v1/chat/completions \

  -H "Authorization: Bearer $GATEWAY_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{
  "model": "auto",
  "messages": [{"role": "user", "content": "Hello!"}]
}'

 # Embeddings

curl https://your-gateway.workers.dev/v1/embeddings \

  -H "Authorization: Bearer $GATEWAY_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{"model": "@cf/baai/bge-base-en-v1.5", "input": "Hello world"}' 