Skip to main content
This is an experimental Worker. Use it as a starting point for your own projects.
The Cloud AI Proxy experiment exposes Workers AI through a single public endpoint. You pass a model ID and prompt (or chat messages) and receive AI-generated text. Use it to try different models or integrate Workers AI from external tools without managing Wrangler or bindings yourself.
The endpoint is public by design. For production use, add rate limiting or API key authentication.

​
Features

  • Call any Workers AI text-generation model via one endpoint
  • Support for single prompt or chat-style messages
  • Optional max_tokens control
  • POST (JSON) and GET (query params) interfaces
  • No external API keys; uses your Cloudflare account’s Workers AI

​
API Reference

​
POST /chat

Send a JSON body with model and prompt or messages.
FieldRequiredDescription
modelYesWorkers AI model ID (e.g. @cf/meta/llama-3.1-8b-instruct-fast)
promptNo*Single prompt string
messagesNo*Array of { role: string, content: string } for chat-style input
max_tokensNoMax tokens to generate (1–4096)
*At least one of prompt or messages is required.
​
response
string
The AI-generated text.

​
Example Request

curl -X POST https://your-worker.workers.dev/chat \
  -H "Content-Type: application/json" \
  -d '{"model":"@cf/meta/llama-3.1-8b-instruct-fast","prompt":"Say hello in one sentence."}'

​
Example Response

{
  "response": "Hello! How can I help you today?"
}

​
GET /chat

Query params: model (required), prompt (required), optional max_tokens.
​
model
string
required
Workers AI model ID (e.g. @cf/meta/llama-3.1-8b-instruct-fast).
​
prompt
string
required
The prompt text. URL-encoded.
​
max_tokens
number
Max tokens to generate (1–4096). Optional.

​
Example Request

curl "https://your-worker.workers.dev/chat?model=@cf/meta/llama-3.1-8b-instruct-fast&prompt=Say%20hello"

​
Error Responses

  • 400 Bad Request — INVALID_BODY, MISSING_MODEL, MISSING_PROMPT, or INVALID_MAX_TOKENS
  • 502 Bad Gateway — AI_ERROR (model run failed)

​
Run locally

1

Clone and enter the experiment

git clone https://github.com/shrinathsnayak/cloudflare-experiments
cd cloudflare-experiments/experiments/cloud-ai-proxy
2

Install and start the dev server

npm install
npm run dev
3

Call the endpoint

Use http://localhost:8787/chat with POST (JSON body) or GET (query params).
Requires a Cloudflare account with Workers AI enabled. See Workers AI for setup.

​
Deploy

Deploy to Cloudflare Workers Deploy from shrinathsnayak/cloudflare-experiments. To use your own fork, change the owner in the deploy URL.

​
Cloudflare features used

  • Workers — Edge runtime
  • Workers AI — AI binding for text generation

Workers AI models

GitHub repository