Mistral Small 3

Mistral

mistral/mistral-small-24b-instruct-2501Open Weights

Efficient Mistral model for fast chat, extraction, and production assistants

Benchmark Pricing$0.12 / 1M in$0.35 / 1M out

Context: 32,768 tokens•Max Output: 16,384 tokens•Knowledge: 2023-10-31•Released: 2025-01-30

TECHNICAL SPECIFICATIONS

Context Window32,76832.8K tokens

Max Output16,38416.4K tokens

LicenseOpen SourceSelf-hostable

Input Modalities

Text

Function / Tool CallingNot Supported

Structured OutputsPrompt Based

MODEL CONTEXT PROTOCOL (MCP) READINESS

⚠ Mistral Small 3 does not natively advertise tool-calling capabilities. When connecting to MCP servers, function calling must be handled via structured prompt injection.

MCP Context Window Recommendations

With a context capacity of 32,768 tokens, this model can handle compact tool sets. Consider keeping MCP server tool manifests minimal to preserve headroom.

API CALL INVOCATION EXAMPLE

// Example: Calling Mistral Small 3 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-small-24b-instruct-2501",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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