MMistral · Released Jun 20, 2025
Mistral Small 3.2 24B
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…
- Released
- Jun 20 2025
- Context window
- 256K 16K out
- Input / 1M tokens
- $0.094 from $0.075
- Output / 1M tokens
- $0.25 from $0.20
Where to run it
4 providers compared
Cheapest: DeepInfra at $0.075 / $0.20 per 1M input / output tokens — 29% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| DeepInfraFP8 | $0.075 | $0.20 | — | 128K | 16K | 99.9%24h | Cheapest |
| VeniceFP8 | $0.094 | $0.25 | — | 256K | 16K | 99.9%24h | +25% |
| ParasailBF16 · no tool calling | $0.09 | $0.30 | $0.05 | 131K | 33K | 97.8%24h | +34% |
| Mistraleu | $0.10 | $0.30 | $0.01 | 33K | 26K | 100%24h | +41% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Mistral Small 3.2 24B. Scores appear here automatically once it does.
Specs
Details
- Model ID
mistralai/mistral-small-3.2-24b-instruct- Developer
- Mistral
- Release date
- Jun 20, 2025 ·
- Context window
- 256,000 tokens
- Max output
- 16,384 tokens
- API price
- $0.094 / $0.25 per 1M input / output tokens
- Providers
- 4
- Input types
- image, text
- Reasoning
- No
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date, prices and providers from OpenRouter's catalog; buying directly from a provider can cost a little differently. Uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.