modelgrep
M

Mistral: Mistral Small 3.2 24B

mistralai/mistral-small-3.2-24b-instruct

Cheaper than 88% of paidToolsJSONVision
Use via OpenRouter ↗
Intelligence
Design Elo
971
Data Viz
Speed
72
100th fastest
Latency
353ms
first token
Input price
$0.075
36th cheapest
Context
128K
16K max out

How it compares

Faster than68%
of all ranked models
Cheaper than88%
of all ranked models

Overview

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...

Benchmarks

independent · via OpenRouter
Design Arena · Elo567 tournaments
Data Viz
971
UI Component
964
codecategories
959
Game Dev
957
Website
940

Providers & pricing (4)

ProviderIn $/MOut $/MUptime
DeepInfrafp8$0.075$0.20099.1%
Parasailbf16$0.090$0.30099.6%
Venicefp8$0.094$0.25099.8%
Mistral$0.100$0.30099.2%

Specifications

Context window128K
Max output16K
Knowledge cutoffOct 2023
Input modalitiesimage, text
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Mistral Small 3.2 24B FAQ

How much does Mistral Small 3.2 24B cost?

Mistral Small 3.2 24B costs $0.075 per million input tokens and $0.200 per million output tokens via OpenRouter, making it 36th cheapest of 298 paid models.

How fast is Mistral Small 3.2 24B?

Mistral Small 3.2 24B generates around 72 tokens per second with 353ms time-to-first-token (p50), the 100th fastest tracked model.

What is Mistral Small 3.2 24B's context window?

Mistral Small 3.2 24B supports a 128K-token context window and can output up to 16K tokens. It accepts image, text input.

Compare head-to-head