Meta Llama 4 Maverick — free API at $0 in/out

Update, 2026-07-27: meta/llama-4-maverick-17b-128e-instruct is no longer served. It has been removed from the upstream NVIDIA NIM catalog, so calling that id now returns a 404. This post is kept because the architecture discussion below is still accurate and people search for it, but every runnable example here uses meta/llama-3.3-70b-instruct, which we verify is serving. The full live list is one request away: curl https://api.inferall.ai/ai/v1/models.

Meta's open models are available free via NVIDIA NIM through InferAll. No credit card, no billing setup: create a key and start calling one now.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.inferall.ai/v1",
    api_key="ifu_your_key_here",  # get one at inferall.ai/keys
)

response = client.chat.completions.create(
    model="meta/llama-3.3-70b-instruct",
    messages=[{"role": "user", "content": "What makes a mixture-of-experts model different from a dense one?"}],
    max_tokens=512,
)

print(response.choices[0].message.content)

---

What is Llama 4 Maverick?

Llama 4 Maverick is Meta's 17B active parameter Mixture of Experts (MoE) model with 128 experts (17b-128e). The MoE architecture activates a subset of its 128 expert networks per token, giving it performance significantly above its active parameter count while keeping inference costs low.

Maverick sits in the Llama 4 family alongside Llama 4 Scout (smaller, faster) and is optimized for instruction-following, reasoning, and code. It's available for free hosting on NVIDIA NIM, which InferAll routes to at zero cost.

---

TypeScript / Node.js

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferall.ai/v1",
  apiKey: process.env.INFERALL_API_KEY,
});

const response = await client.chat.completions.create({
  model: "meta/llama-3.3-70b-instruct",
  messages: [{ role: "user", content: "Explain mixture of experts architectures." }],
});

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

Streaming

with client.chat.completions.create(
    model="meta/llama-3.3-70b-instruct",
    messages=[{"role": "user", "content": "Walk me through mixture-of-experts architectures."}],
    stream=True,
) as stream:
    for chunk in stream:
        print(chunk.choices[0].delta.content or "", end="")

Claude Code / Cline / Cursor

Point any Anthropic-compatible client at InferAll and Llama 4 Maverick routes under the "opus" tier:

export ANTHROPIC_BASE_URL=https://api.inferall.ai
export ANTHROPIC_API_KEY=ifu_your_key_here

---

Free models on InferAll (selection)

Model	Size	Notes
meta/llama-4-maverick-17b-128e-instruct	17B×128E MoE	Retired upstream. No longer served.
meta/llama-3.3-70b-instruct	70B	Strong general purpose
meta/llama-3.1-70b-instruct	70B	Stable workhorse
nvidia/nemotron-3-super-120b-a12b	120B	NVIDIA's largest free model
mistralai/mistral-medium-3.5-128b	46.7B MoE	Fast, efficient

The full free model list is always available at the API — filter by inputPerM: 0.

---

Get started

inferall.ai/keys — sign up free and start calling (25 free NIM calls before any payment; the $5 starter pack unlocks ongoing use) at /billing. The $5 becomes spendable balance: 40+ open NIM models stay $0 in/out against it (within the free-plan daily request caps); premium providers (OpenAI, Anthropic, Google) bill at the provider's published per-token rate with zero markup.