@cf/meta/llama-4-scout-17b-16e-instruct — Free API

What is @cf/meta/llama-4-scout-17b-16e-instruct?

Llama 4 Scout 17B is Meta's latest-generation small-footprint model with an exceptionally large 10M-token context window — meaning you can ingest entire codebases, multi-hour transcripts, or thousand-page documents in a single request. Running on Cloudflare's global edge network, it combines the efficiency of a 17B-parameter model (with 16 active experts via MoE) with a context size that exceeds most flagship models. On the free tier it shares the 10,000 Neurons/day pool and uses Cloudflare's native API. For developers evaluating long-context architectures or building retrieval-free RAG alternatives, this is one of the few free options that can genuinely test 10M-token prompts.

@cf/meta/llama-4-scout-17b-16e-instruct 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-4-scout-17b-16e-instruct",
    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-4-scout-17b-16e-instruct",
  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-4-scout-17b-16e-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Other Free Models from Cloudflare Workers AI