Mistral Small 3.2 24B pricing & benchmarks
Released Jun 20, 2025 · served by 3 providers
What Mistral Small 3.2 24B is
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...
- Model ID:
mistralai/mistral-small-3.2-24b-instruct - Modality: text+image->text
- Knowledge cutoff: 2023-10-31
- Tool calling: supported · Structured output: supported
- Weights:
mistralai/Mistral-Small-3.2-24B-Instruct-2506on Hugging Face
Providers and prices for Mistral Small 3.2 24B
The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| DeepInfracheapest | $0.075 | $0.200 | 128K | fp8 | 99.4% | — |
| Venice | $0.094 | $0.250 | 256K | fp8 | 97.1% | — |
| Mistral | $0.100 | $0.300 | 131K | — | 99.8% | — |
Mistral Small 3.2 24B benchmark results
Design Arena head-to-head results, as reported through the OpenRouter model API.
| Category | Arena | Rank | Elo | Win rate |
|---|---|---|---|---|
| dataviz | models | #101 | 957 | 43.3% |
| uicomponent | models | #101 | 944 | 40.5% |
| gamedev | models | #107 | 945 | 39.4% |
| codecategories | models | #109 | 938 | 39.8% |
| website | models | #112 | 920 | 38.3% |
FAQ
How much does the Mistral Small 3.2 24B API cost?
$0.075 per 1M input tokens and $0.200 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.14.
Is Mistral Small 3.2 24B free?
No. It is a paid model starting at $0.075 per 1M input tokens, though some providers offer trial credits.
Which provider is cheapest for Mistral Small 3.2 24B?
DeepInfra at $0.075 input / $0.200 output per 1M tokens (fp8 quantization).
Can I self-host Mistral Small 3.2 24B?
Yes — weights are published as mistralai/Mistral-Small-3.2-24B-Instruct-2506 on Hugging Face, so you can run it on your own hardware.