Workers AI
Cloudflare's serverless inference for running open models on GPUs across its global network, from Workers or a REST API.
About Workers AI
Running models close to users without managing GPU servers is hard for small teams.
Who it’s for
- Developers already building on Cloudflare Workers
- Teams that want serverless inference at the edge
When to consider it
Consider Workers AI when your app runs on Cloudflare and you want open models without managing infrastructure.
Tradeoffs & limitations
- Includes 10,000 free Neurons a day; usage beyond that is billed per 1,000 Neurons on the paid Workers plan.
SOTA overview · Documentation-based assessment · Sources & review method
Updates
No updates shared yet.
Discussion
Newest firstAsk a question or share how you use Workers AI.
Keep it helpful. Community rules
Loading discussion…
Sources & review method
Documentation-based assessment · Oct 2, 2026 · Prepared with AI assistance; not a hands-on benchmark.
Checked by SOTA · AI-assisted documentation review. Selection advice is our assessment; verify current requirements for your deployment.
Import history & original evidence
Workers AI official website
Cloudflare's serverless inference for running open models on GPUs across its global network, from Workers or a REST API.
Based on official pages and announcements checked on 2026-10-02. No hands-on test, performance benchmark or popularity ranking is claimed.