Mistral: Mistral Small 3.2 24B
mistralai/mistral-small-3.2-24b-instruct
Cheaper than 83% of paidToolsJSONVision
Intelligence
—
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.100
55th cheapest
Context
256K
How it compares
Cheaper than83%
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...
Providers & pricing (4)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfrafp8 | $0.075 | $0.200 | 128K | 99.6% |
| Parasailbf16 | $0.090 | $0.300 | 131K | 99.9% |
| Venicefp8 | $0.094 | $0.250 | 256K | 99.4% |
| Mistral | $0.100 | $0.300 | 131K | 100% |
Specifications
Context window256K
Max output—
Knowledge cutoffOct 2023
Input modalitiesimage, text
Output modalitiestext
Prompt caching—
Cache read price$0.010/M
ModeratedNo
Open weightsmistralai/Mistral-Small-3.2-24B-Instruct-2506 ↗
Mistral Small 3.2 24B FAQ
How much does Mistral Small 3.2 24B cost?
Mistral Small 3.2 24B costs $0.100 per million input tokens and $0.300 per million output tokens via OpenRouter, making it 55th cheapest of 332 paid models.
What is Mistral Small 3.2 24B's context window?
Mistral Small 3.2 24B supports a 256K-token context window. It accepts image, text input.
More from mistralai
All Mistral Small 3.2 24B alternatives →Compare head-to-head
Mistral: Mistral Small 3.2 24B vs Mistral: Mistral Medium 3.5Mistral: Mistral Small 3.2 24B vs Mistral: Mistral Small 4Mistral: Mistral Small 3.2 24B vs Mistral: Devstral 2 2512Mistral: Mistral Small 3.2 24B vs Mistral: Ministral 3 14B 2512Mistral: Mistral Small 3.2 24B vs Mistral: Ministral 3 8B 2512Mistral: Mistral Small 3.2 24B vs Mistral: Ministral 3 3B 2512