Powered by Cloudflare AI
Workers AI
Run AI inference at the edge with zero cold starts. Access 100+ models including LLaMA, Stable Diffusion, and Whisper.
100+
AI Models
0ms
Cold Start
10K
Free Neurons/day
Global
Edge Inference
Available Models
Text Generation
- LLaMA 3.1 70B
- Mistral 7B
- Gemma 2 27B
- Qwen 2.5
Image Generation
- Stable Diffusion XL
- FLUX.1 Schnell
- DreamShaper
Speech
- Whisper (transcription)
- Text-to-Speech
- Voice cloning
Embeddings
- BGE Base
- BGE Large
- Multilingual
Simple API
Text Generation
const response = await ai.run('@cf/meta/llama-3.1-70b', {
prompt: 'Explain quantum computing in simple terms',
stream: true,
max_tokens: 500
});
// Stream the response
for await (const chunk of response) {
console.log(chunk);
}
Image Generation
const response = await ai.run('@cf/stabilityai/stable-diffusion-xl', {
prompt: 'A futuristic city at sunset, cyberpunk style',
width: 1024,
height: 1024
});
// Returns PNG image buffer
return new Response(response, {
headers: { 'Content-Type': 'image/png' }
});
Pricing
Workers AI
Serverless AI inference at the edge
Free
- 10000 neurons/day
- Edge inference
- 100+ models
- REST API
- Streaming
Workers AI Pro
Production AI at scale
$50.0/mo
- Unlimited neurons
- Unlimited inference
- Fine-tuned models
- Vectorize integration
- Priority support
AI Without the Infrastructure
10,000 free neurons daily. No GPU management required.
Start Building with AI