Every integration below ships configured in FastAPI AI Kit. Drop in your API key and go.
Connect to GPT-4o and the full OpenAI API in minutes.
Run Claude 3.5 Sonnet and Claude 3 Opus via FastAPI.
Usage-based billing wired to every API call.
Async PostgreSQL with pgvector, migrations, and connection pooling.
Managed Postgres, Auth, and Storage — drop Supabase in as your backend.
Rate limiting, session cache, and job queues — all via Redis.
Production vector search with Qdrant — swap from pgvector with one env var.
Deploy FastAPI AI Kit to Railway in under 5 minutes.
One-click FastAPI deploy on Render with Postgres and Redis.
Use LangChain RAG chains as an optional layer in the kit.
Async task processing wired up and ready for background LLM jobs.
