Mistral Medium 3.5

MistralMCP Tool CallReasoning

mistral/mistral-medium-2604Open Weights

Balanced Mistral model for enterprise assistants, multilingual work, and tools

Benchmark Pricing$1.50 / 1M in$7.50 / 1M out$0.15 cache read

Context: 262,144 tokens•Max Output: 262,144 tokens•Released: 2026-04-29

TECHNICAL SPECIFICATIONS

Context Window262,144262.1K tokens

Max Output262,144262.1K tokens

LicenseOpen SourceSelf-hostable

Input Modalities

TextVision

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Mistral Medium 3.5 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 262,144 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

STANDARDIZED BENCHMARKS & EVALS

SWE-Bench Verifiedresolved

77.6

τ³-Telecomaccuracy

91.4

API CALL INVOCATION EXAMPLE

// Example: Calling Mistral Medium 3.5 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/mistral-medium-2604",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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