Voxtral Small (latest)

MistralMCP Tool Call

mistral/voxtral-small-latestOpen Weights

Instruct model with native audio input for speech understanding and tool use

Benchmark Pricing$0.10 / 1M in$0.40 / 1M out

Context: 32,000 tokens•Max Output: 32,000 tokens•Released: 2025-07-15

TECHNICAL SPECIFICATIONS

Context Window32,00032K tokens

Max Output32,00032K tokens

LicenseOpen SourceSelf-hostable

Input Modalities

TextAudio

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Voxtral Small (latest) 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 32,000 tokens, this model can handle compact tool sets. Consider keeping MCP server tool manifests minimal to preserve headroom.

API CALL INVOCATION EXAMPLE

// Example: Calling Voxtral Small (latest) 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/voxtral-small-latest",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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