Cloudflare Workers AI

Cloudflare Workers AI

Status: Production Ready ✅ Last Updated: 2025-11-25 Dependencies: cloudflare-worker-base (for Worker setup) Latest Versions: wrangler@4.50.0, @cloudflare/workers-types@4.20251125.0

Recent Updates (2025):

• April 2025 - Performance: Llama 3.3 70B 2-4x faster (speculative decoding, prefix caching), BGE embeddings 2x faster
• April 2025 - Breaking Changes: max_tokens now correctly defaults to 256 (was not respected), BGE pooling parameter (cls NOT backwards compatible with mean)
• 2025 - New Models (14): Mistral 3.1 24B (vision+tools), Gemma 3 12B (128K context), EmbeddingGemma 300M, Llama 4 Scout, GPT-OSS 120B/20B, Qwen models (QwQ 32B, Coder 32B), Leonardo image gen, Deepgram Aura 2, Whisper v3 Turbo, IBM Granite, Nova 3
• 2025 - Platform: Context windows API change (tokens not chars), unit-based pricing with per-model granularity, workers-ai-provider v2.0.0 (AI SDK v5), LoRA rank up to 32 (was 8), 100 adapters per account
• October 2025: Model deprecations (use Llama 4, GPT-OSS instead)

Quick Start (5 Minutes)

// 1. Add AI binding to wrangler.jsonc
{ "ai": { "binding": "AI" } }

// 2. Run model with streaming (recommended)
export default {
  async fetch(request: Request, env: Env): Promise<Response> {
    const stream = await env.AI.run('@cf/meta/llama-3.1-8b-instruct', {
      messages: [{ role: 'user', content: 'Tell me a story' }],
      stream: true, // Always stream for text generation!
    });

    return new Response(stream, {
      headers: { 'content-type': 'text/event-stream' },
    });
  },
};

Why streaming? Prevents buffering in memory, faster time-to-first-token, avoids Worker timeout issues.

API Reference

env.AI.run(
  model: string,
  inputs: ModelInputs,
  options?: { gateway?: { id: string; skipCache?: boolean } }
): Promise<ModelOutput | ReadableStream>

Model Selection Guide (Updated 2025)

Text Generation (LLMs)

Text Embeddings (2x Faster - 2025)

CRITICAL (2025): BGE models now support pooling: "cls" parameter (recommended) but NOT backwards compatible with pooling: "mean" (default).

Image Generation

Vision Models

Audio Models (2025)

Common Patterns

RAG (Retrieval Augmented Generation)

// 1. Generate embeddings
const embeddings = await env.AI.run('@cf/baai/bge-base-en-v1.5', { text: [userQuery] });

// 2. Search Vectorize
const matches = await env.VECTORIZE.query(embeddings.data[0], { topK: 3 });
const context = matches.matches.map((m) => m.metadata.text).join('\n\n');

// 3. Generate with context
const response = await env.AI.run('@cf/meta/llama-3.1-8b-instruct', {
  messages: [
    { role: 'system', content: `Answer using this context:\n${context}` },
    { role: 'user', content: userQuery },
  ],
  stream: true,
});

Structured Output with Zod

import { z } from 'zod';

const Schema = z.object({ name: z.string(), items: z.array(z.string()) });

const response = await env.AI.run('@cf/meta/llama-3.1-8b-instruct', {
  messages: [{
    role: 'user',
    content: `Generate JSON matching: ${JSON.stringify(Schema.shape)}`
  }],
});

const validated = Schema.parse(JSON.parse(response.response));

AI Gateway Integration

Provides caching, logging, cost tracking, and analytics for AI requests.

const response = await env.AI.run(
  '@cf/meta/llama-3.1-8b-instruct',
  { prompt: 'Hello' },
  { gateway: { id: 'my-gateway', skipCache: false } }
);

// Access logs and send feedback
const gateway = env.AI.gateway('my-gateway');
await gateway.patchLog(env.AI.aiGatewayLogId, {
  feedback: { rating: 1, comment: 'Great response' },
});

Benefits: Cost tracking, caching (reduces duplicate inference), logging, rate limiting, analytics.

Rate Limits & Pricing (Updated 2025)

Rate Limits (per minute)

Pricing (Unit-Based, Billed in Neurons - 2025)

Free Tier:

• 10,000 neurons per day
• Resets daily at 00:00 UTC

Paid Tier ($0.011 per 1,000 neurons):

• 10,000 neurons/day included
• Unlimited usage above free allocation

2025 Model Costs (per 1M tokens):

Error Handling with Retry

async function runAIWithRetry(
  env: Env,
  model: string,
  inputs: any,
  maxRetries = 3
): Promise<any> {
  let lastError: Error;

  for (let i = 0; i < maxRetries; i++) {
    try {
      return await env.AI.run(model, inputs);
    } catch (error) {
      lastError = error as Error;

      // Rate limit - retry with exponential backoff
      if (lastError.message.toLowerCase().includes('rate limit')) {
        await new Promise((resolve) => setTimeout(resolve, Math.pow(2, i) * 1000));
        continue;
      }

      throw error; // Other errors - fail immediately
    }
  }

  throw lastError!;
}

OpenAI Compatibility

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: env.CLOUDFLARE_API_KEY,
  baseURL: `https://api.cloudflare.com/client/v4/accounts/${env.ACCOUNT_ID}/ai/v1`,
});

// Chat completions
await openai.chat.completions.create({
  model: '@cf/meta/llama-3.1-8b-instruct',
  messages: [{ role: 'user', content: 'Hello!' }],
});

Endpoints: /v1/chat/completions, /v1/embeddings

Vercel AI SDK Integration (workers-ai-provider v2.0.0)

import { createWorkersAI } from 'workers-ai-provider'; // v2.0.0 with AI SDK v5
import { generateText, streamText } from 'ai';

const workersai = createWorkersAI({ binding: env.AI });

// Generate or stream
await generateText({
  model: workersai('@cf/meta/llama-3.1-8b-instruct'),
  prompt: 'Write a poem',
});

References

• Workers AI Docs
• Models Catalog
• AI Gateway
• Pricing
• Changelog
• LoRA Adapters
• MCP Tool: Use mcp__cloudflare-docs__search_cloudflare_documentation for latest docs