modelgrep
M

Mistral Large

mistralai/mistral-large

ToolsJSON
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
42
197th fastest
Latency
573ms
first token
Input price
$2.00
251st cheapest
Context
128K

How it compares

Faster than33%
of all ranked models
Cheaper than16%
of all ranked models

Overview

This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....

Benchmarks

independent · via OpenRouter
Artificial Analysis
GPQA Diamond
35%
Humanity's Last Exam
3%
SciCode
21%

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Mistral$2.00$6.00100%

Specifications

Context window128K
Max output
Knowledge cutoffNov 2024
Input modalitiestext, file
Output modalitiestext
Prompt caching
Cache read price$0.200/M
ModeratedNo

Mistral Large FAQ

How much does Mistral Large cost?

Mistral Large costs $2.00 per million input tokens and $6.00 per million output tokens via OpenRouter, making it 251st cheapest of 298 paid models.

How fast is Mistral Large?

Mistral Large generates around 42 tokens per second with 573ms time-to-first-token (p50), the 197th fastest tracked model.

What is Mistral Large's context window?

Mistral Large supports a 128K-token context window. It accepts text, file input.

Compare head-to-head