Llama 4 Maverick 17B Instruct

MetaMCP Tool Call

meta/llama-4-maverick-17b-instructOpen Weights

Open multimodal Llama for strong reasoning with efficient everyday serving

Benchmark Pricing$0.72 / 1M in$0.72 / 1M out

Context: 1,000,000 tokens•Max Output: 16,384 tokens•Knowledge: 2024-08•Released: 2025-04-05

TECHNICAL SPECIFICATIONS

Context Window1,000,0001M tokens

Max Output16,38416.4K tokens

LicenseOpen SourceSelf-hostable

Input Modalities

TextVision

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Llama 4 Maverick 17B Instruct natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 1,000,000 tokens, this model can handle extremely large MCP resource manifests, complete database schemas, and multiple active server tool definitions simultaneously without degradation.

STANDARDIZED BENCHMARKS & EVALS

Aider Polyglotpercent correct

15.6

SWE-Bench Proresolve rate

5.24

API CALL INVOCATION EXAMPLE

// Example: Calling Llama 4 Maverick 17B Instruct via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.META_API_KEY,
});

const response = await client.chat.completions.create({
  model: "meta/llama-4-maverick-17b-instruct",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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