Replicate

Run open-source AI models via API.

What is Replicate?

Run open-source AI models via API. Deploy your own models or use the model gallery.

Serverless cloud for AI workloads.

Ultra-low-latency LPU inference.

Hosted inference for open models.

High-throughput LLM serving engine.

Newsletter

Updates from the AI world — what shipped, what we’re using in production, and what’s worth your attention. Two emails a month, no spam.