Home

ai api

Cloudflare Workers AI

Cloudflare Workers AI is a serverless inference service for supported models on Cloudflare's network, accessible through Workers bindings and a REST API. Its catalog covers language, embedding, image, audio, and other tasks.

Data status: partially_verified · Checked: 2026-10-16

Good fit if

Serverless inference without managing GPU instances

May not fit if

The free allocation is 10,000 Neurons per day; limits reset at 00:00 UTC and further requests fail after the allocation is exceeded on Workers Free.

Price

0 USD

Pricing source ↗
Official website ↗

Features and benefits

  • Serverless inference without managing GPU instances
  • Model catalog covers LLM, embeddings, image, and audio tasks
  • Access through Workers bindings and REST API
  • Usage measured in Neurons with published per-model prices

Limitations

  • The free allocation is 10,000 Neurons per day; limits reset at 00:00 UTC and further requests fail after the allocation is exceeded on Workers Free.
  • Workers Paid is required for usage above the daily allocation.
  • Some models require a paid billing method; model availability and limits vary.

Pricing

Free daily allocation

0 USD · free

10,000 Neurons per day at no charge; resets at 00:00 UTC.

Pricing source

Workers Paid usage above allocation

0.011 USD · usage_based

Per 1,000 Neurons above the daily free allocation. Model-specific token and task equivalents vary.

Pricing source

Sources