Cloudflare Workers AI

Run AI inference at the edge on Cloudflare's global network

Code & DevelopmentFreemium

Cloudflare Workers AI enables developers to run AI inference at the edge using Cloudflare's global network of 300+ data centers. By running models close to users, Workers AI delivers low-latency AI features — text generation, image classification, speech recognition, and embedding generation — without provisioning dedicated GPU infrastructure. It supports a curated catalog of popular open-source models and integrates seamlessly with other Cloudflare products like Pages, D1, and R2.

Key Features

• ✓Edge inference
• ✓300+ data centers
• ✓No GPU provisioning
• ✓Popular model catalog
• ✓Embedding generation
• ✓Workers integration