Cloudflare Workers AI Has a Free API: Run AI Models at the Edge with Zero Infrastructure

npm create cloudflare@latest my-ai-app -- --template worker-typescript
cd my-ai-app

# wrangler.toml
[ai]
binding = "AI"

export default {
  async fetch(request: Request, env: Env) {
    const response = await env.AI.run("@cf/meta/llama-3.1-8b-instruct", {
      messages: [
        { role: "system", content: "You are a helpful assistant." },
        { role: "user", content: "Explain WebAssembly in 3 sentences." },
      ],
      max_tokens: 256,
    });

    return Response.json(response);
  },
};

const stream = await env.AI.run("@cf/meta/llama-3.1-8b-instruct", {
  messages: [{ role: "user", content: "Write a poem about coding" }],
  stream: true,
});

return new Response(stream, {
  headers: { "Content-Type": "text/event-stream" },
});

const embeddings = await env.AI.run("@cf/baai/bge-base-en-v1.5", {
  text: ["How to deploy a web app", "Best practices for CI/CD"],
});

console.log(embeddings.data[0].length); // 768 dimensions

const imageData = await request.arrayBuffer();
const result = await env.AI.run("@cf/microsoft/resnet-50", {
  image: [...new Uint8Array(imageData)],
});

console.log(result); // [{label: "cat", score: 0.95}, ...]

const image = await env.AI.run("@cf/stabilityai/stable-diffusion-xl-base-1.0", {
  prompt: "A futuristic city skyline at sunset, cyberpunk style",
});

return new Response(image, {
  headers: { "Content-Type": "image/png" },
});

const translated = await env.AI.run("@cf/meta/m2m100-1.2b", {
  text: "Hello, how are you?",
  source_lang: "english",
  target_lang: "spanish",
});
// {translated_text: "Hola, ¿cómo estás?"}

const audioData = await request.arrayBuffer();
const transcription = await env.AI.run("@cf/openai/whisper", {
  audio: [...new Uint8Array(audioData)],
});
console.log(transcription.text);

const summary = await env.AI.run("@cf/facebook/bart-large-cnn", {
  input_text: longArticleText,
  max_length: 150,
});

curl "https://api.cloudflare.com/client/v4/accounts/ACCOUNT_ID/ai/run/@cf/meta/llama-3.1-8b-instruct" 
  -H "Authorization: Bearer $CF_TOKEN" 
  -d '{"messages": [{"role": "user", "content": "Hello"}]}'