Llama 3.2 3B Instruct

MetaMCP Tool Call

meta/llama-3.2-3b-instructOpen Weights

Small instruction-tuned Llama model for multilingual dialogue and agentic retrieval

Benchmark Pricing$0.03 / 1M in$0.05 / 1M out$0.02 cache read

Context: 131,072 tokens•Max Output: 131,072 tokens•Knowledge: 2023-12•Released: 2024-09-25

TECHNICAL SPECIFICATIONS

Context Window131,072131.1K tokens

Max Output131,072131.1K tokens

LicenseLlama 3.2 Community LicenseSelf-hostable

Input Modalities

Text

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Llama 3.2 3B 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 131,072 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling Llama 3.2 3B 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-3.2-3b-instruct",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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