Mistral Large

MistralMCP Tool Call

mistral/mistral-largeClosed API

Flagship Mistral model for advanced reasoning, coding, and multilingual work

Benchmark Pricing$4.28 / 1M in$12.95 / 1M out

Context: 128,000 tokens•Max Output: 102,400 tokens•Knowledge: 2024-11-30•Released: 2024-02-26

TECHNICAL SPECIFICATIONS

Context Window128,000128K tokens

Max Output102,400102.4K tokens

LicenseProprietaryCloud API only

Input Modalities

TextPDF

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Mistral Large 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 128,000 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling Mistral Large 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-large",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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

PRICING BY PROVIDER

15 providers

Cortecsmistral-large-2402

$4.28 / $12.95

NanoGPTmistralai/mistral-large

$2.01 / $6.00$0.20 cache

Snowflake Cortexmistral-large2

$2.00 / $6.00

302.AImistral-large-2512

$1.10 / $3.30

LLM Gatewaymistral/mistral-large-4

$1.36 / $4.18$0.14 cache

Tempr Gatewaymistral/mistral-large-2512

$0.50 / $1.50$0.05 cache

AI/ML APImistralai/mistral-large

$2.75 / $8.25$0.28 cache

Vercel AI Gatewaymistral/mistral-large-4

$1.36 / $4.18$0.14 cache

OpenCodemistral-large-4

$0.68 / $2.09$0.07 cache

Eden AImistral/mistral-large-2407

$2.00 / $6.00$0.20 cache

Merge Gatewaymistral/mistral-large-2411

$2.00 / $6.00

Prime Inferencemistralai/mistral-large-2512

$0.50 / $1.50

LowRouterauto/mistralai/mistral-large-4

$1.44 / $4.42$0.15 cache

Amazon Bedrockmistral.mistral-large-3-675b-instruct

$0.50 / $1.50

Kilo Gatewaymistralai/mistral-large

$2.00 / $6.00$0.20 cache

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

MODEL RESOURCES

View Mistral Hub

More Models by Mistral

Alternative and family models from the same lab

View all Mistral models →

Mistral Large 4

mistral/mistral-large-4•Mistral

Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work

262.1K out maxVision

In: $0.68 • Out: $2.09

Mistral Medium 3.5

mistral/mistral-medium-3-5•Mistral

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

209.7K out maxVisionPDF

In: $1.50 • Out: $7.50

mistral/ministral-14b•Mistral

Compact multimodal Mistral model for local assistants, edge agents, and efficient tool use

262.1K out maxVision

In: $0.24 • Out: $0.24