From cloudflare
Use this skill when the user asks about Cloudflare Workers AI, running AI inference on Cloudflare's edge, using AI models in Workers, or managing Workers AI resources with Pulumi.
npx claudepluginhub nsheaps/ai-mktpl --plugin cloudflareThis skill uses the workspace's default tool permissions.
Workers AI lets you run AI models on Cloudflare's GPU-powered edge network. Access open-source models (LLMs, image generation, embeddings, speech-to-text) directly from Workers with zero infrastructure management.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Guides agent creation for Claude Code plugins with file templates, frontmatter specs (name, description, model), triggering examples, system prompts, and best practices.
Workers AI lets you run AI models on Cloudflare's GPU-powered edge network. Access open-source models (LLMs, image generation, embeddings, speech-to-text) directly from Workers with zero infrastructure management.
cloudflare.WorkersScript with aiBindingexport default {
async fetch(request: Request, env: Env): Promise<Response> {
const response = await env.AI.run("@cf/meta/llama-3.1-8b-instruct", {
messages: [{ role: "user", content: "What is Cloudflare?" }],
});
return Response.json(response);
},
};
interface Env {
AI: Ai;
}
[ai]
binding = "AI"
| Model | Task | ID |
|---|---|---|
| Llama 3.1 8B | Text generation | @cf/meta/llama-3.1-8b-instruct |
| Mistral 7B | Text generation | @cf/mistral/mistral-7b-instruct-v0.2 |
| BAAI BGE | Text embeddings | @cf/baai/bge-base-en-v1.5 |
| Stable Diffusion XL | Image generation | @cf/stabilityai/stable-diffusion-xl-base-1.0 |
| Whisper | Speech-to-text | @cf/openai/whisper |
Workers AI also has a REST API (no Worker needed):
curl "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/meta/llama-3.1-8b-instruct" \
-H "Authorization: Bearer $CF_API_TOKEN" \
-d '{"messages": [{"role": "user", "content": "Hello"}]}'
// Workers AI is accessed via a binding on a Worker — no separate resource needed
const worker = new cloudflare.WorkersScript("ai-worker", {
accountId,
name: "ai-worker",
content: workerScript,
module: true,
// AI binding is automatic when using the AI API in the Worker
});
| Tier | Neurons/day | Cost |
|---|---|---|
| Free | 10,000 | $0 |
| Paid | Unlimited | $0.011 per 1,000 neurons |
Neurons are a normalized unit of compute across all models.