Skip to main content
Relay Free-Quota DB
Back to list
Cloudflare Workers AI

Cloudflare Workers AI

Tokens

2 models · 2 Providers

Overview

API base
https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1
Env vars
CLOUDFLARE_API_TOKEN
Docs
—
Auth
API Key
OpenAI compatible
Pricing
Retail
Region
Global
Status
Operational
Updated
2026-08-20
Features
OpenAI compatible
Serverless

Free quota

Daily free inference quota (~10,000 requests/day)

Workers AI provides ~10,000 inferences per day on the free tier. The OpenAI-compatible endpoint requires account_id.

Providers (2)

Models offered (2)

ModelIDContextMax outputPrice ($/1M tokens)ReasoningTool callStructuredAvailable on
Llama 3.1 8Bmeta/llama-3.1-8b128K8K—?3
Qwen2.5-72B Instructqwen/qwen2.5-72b-instruct128K8K—?3