Ministral 3 14B

MistralMCP Tool Call
mistral/ministral-3-14b-instruct-2512Open Weights

Open vision-language model for efficient local deployment, instruction following, and tool use

Benchmark Pricing$0.20 / 1M in$0.20 / 1M out$0.02 cache read
Context: 262,144 tokens•Max Output: 262,144 tokens•Released: 2025-12-02

TECHNICAL SPECIFICATIONS

Context Window262,144262.1K tokens
Max Output262,144262.1K tokens
LicenseApache 2.0Self-hostable
Input Modalities
TextVision
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Ministral 3 14B 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.

API CALL INVOCATION EXAMPLE

// Example: Calling Ministral 3 14B 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/ministral-3-14b-instruct-2512",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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

PRICING BY PROVIDER

4 providers
Mistralministral-14b-2512
$0.20 / $0.20$0.02 cache
NanoGPTmistralai/ministral-14b-instruct-2512
$0.10 / $0.40$0.05 cache
LowRouterauto/mistralai/ministral-14b-2512
$0.21 / $0.21$0.02 cache
DigitalOceanmistral-3-14B
$0.20 / $0.20$0.04 cache

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

Prompt Caching Active

This model supports prompt caching at $0.02 / 1M tokens, saving up to 90% on repetitive MCP tool definitions and system instructions.