Mistral Small 3.2 24B
Mistral · Multimodal · Released Jun 2025
Mistral Small 3.2 24B is a 24-billion parameter model from Mistral optimized for instruction following and function calling, with a 128k token context window.
- Strengths
- Strong performance on instruction-following tasks and structured outputs like function calls, with reduced repetition compared to earlier versions.
- Best for
- Applications requiring reliable function calling, tool integration, and precise instruction adherence at a moderate model size.
- Limitations
- As a smaller model, it may struggle with complex reasoning tasks, long-form generation, or specialized domains requiring deeper knowledge compared to larger models.
Input / 1M
$0.1
Output / 1M
$0.3
Cached input / 1M
$0.01
Context window
131K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in increased 33.3% out increased 50.0%
- 90d
- in increased 33.3% out increased 50.0%
- 1y
- in increased 33.3% out increased 50.0%
- Since launch
- in increased 33.3% out increased 50.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 15 Jul 2026 | $0.1 | $0.3 | $0.01 | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.075 | $0.2 | — | Imported from OpenRouter | openrouter.ai |