@cf/meta/llama-3.1-8b-instruct-fp8-fast — Free API

What is @cf/meta/llama-3.1-8b-instruct-fp8-fast?

Llama 3.1 8B Instruct on Cloudflare Workers AI is a lightweight, edge-deployed version of Meta's 8B model optimized with FP8 quantization for fast inference. It is the fastest and most cost-efficient option in Cloudflare's free catalog — ideal for high-volume, low-latency tasks like chat routing, text classification, summarization, or simple Q&A where a 70B+ model would be overkill. Like all Cloudflare Workers AI models, it shares the 10,000 Neurons/day free pool and uses a Cloudflare-specific API format. For developers already on Cloudflare's ecosystem, it integrates directly with Workers and Pages with minimal cold start.

@cf/meta/llama-3.1-8b-instruct-fp8-fast API Code Example

Paste your API key and run. See the config generator for Claude Code, Cursor, and more tools.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="cf-meta-llama-3-1-8b-instruct-fp8-fast",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run",
  apiKey: "YOUR_API_KEY",
});

const completion = await openai.chat.completions.create({
  model: "cf-meta-llama-3-1-8b-instruct-fp8-fast",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(completion.choices[0].message.content);

curl https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "cf-meta-llama-3-1-8b-instruct-fp8-fast",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Other Free Models from Cloudflare Workers AI