Llama-4-Maverick-17B-128E — Free API

What is Llama-4-Maverick-17B-128E?

Llama 4 Maverick 17B is Meta's high-expert-count MoE model with 128 active experts, available for free on GitHub Models. Despite its compact 17B active parameter footprint, the large expert pool gives it broad knowledge coverage — making it a strong general-purpose chat and instruction-following model that rivals much larger dense architectures. The free tier limits output to 4K tokens per request with 10 RPM and 50 requests per day, so it is best suited for interactive chat and short-form generation rather than long-form writing. Fully OpenAI SDK-compatible; requires only a GitHub account to start using.

Llama-4-Maverick-17B-128E 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-maverick-17b-128e",
    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-maverick-17b-128e",
  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-maverick-17b-128e",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Other Free Models from GitHub Models