Magistral Small

MistralMCP Tool CallReasoning

mistral/magistral-small-2506Open Weights

Open Mistral reasoning model for transparent step-by-step problem solving

Benchmark Pricing$0.50 / 1M in$1.50 / 1M out$0.50 cache read

Context: 131,072 tokens•Max Output: 8,192 tokens•Released: 2025-06-10

TECHNICAL SPECIFICATIONS

Context Window131,072131.1K tokens

Max Output8,1928.2K tokens

LicenseApache 2.0Self-hostable

Input Modalities

Text

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Magistral Small 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 Magistral Small via OpenAI SDK
import OpenAI from "openai";

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

const response = await client.chat.completions.create({
  model: "mistral/magistral-small-2506",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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