Llama-4-Scout-17B-16E — Free API

What is Llama-4-Scout-17B-16E?

Llama 4 Scout 17B is Meta's efficient long-context model with 16 active experts (MoE), available free on GitHub Models. With a 512K context window — far beyond most free models — it can process entire novels, full code repositories, or multi-hour transcripts in a single request. The 17B total parameter footprint keeps inference fast and cost-effective, making it practical for retrieval-free document analysis and long-form summarization. Rate limits are 15 RPM and 150 requests per day with per-request output capped at 4K tokens. Fully OpenAI SDK-compatible and requires only a GitHub account.

Llama-4-Scout-17B-16E 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://models.github.ai/inference",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="llama-4-scout-17b-16e",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://models.github.ai/inference",
  apiKey: "YOUR_API_KEY",
});

const completion = await openai.chat.completions.create({
  model: "llama-4-scout-17b-16e",
  messages: [{ role: "user", content: "Hello!" }],
});

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

curl https://models.github.ai/inference/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "llama-4-scout-17b-16e",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Other Free Models from GitHub Models