Replicate

A cloud platform for running AI models with a simple API call. Replicate hosts thousands of open-source models — from image generation to speech recognition — letting developers use them without managing GPUs, containers, or infrastructure.

• Model catalog — thousands of open-source models ready to run via API • One-line API — run any model with a single API call, no setup required • Custom models — deploy your own models with Cog, Replicate's open-source packaging tool • Auto-scaling — infrastructure scales to zero when idle, up to thousands of GPUs under load • Community models — browse and run models shared by the community • Predictions API — track inference jobs with webhooks and polling

Pay-per-second of compute. No minimum fees or subscriptions.