Mistral Small 3.2 24B
Efficient Mistral model for fast chat, extraction, and production assistants
mistral/mistral-small-3.2-24b-instruct- Lab
- Mistral
- Family
- mistral-small
- Providers
- 8
- Context
- 256,000
- Output limit
- 16,384
- Knowledge
- 2023-10
- Release
- 2025-06-20
- Updated
- 2025-06-20
- Weights
- Open
- Input
- Output types
- Capabilities
- tools, temperature
Providers
8| AI/ML API | Mistral | mistralai/mistral-small-3.2-24b-instruct | 128,000 | 16,384 | $0.0794 / $0.2116 | No | Yes | Yes | Yes |
|---|---|---|---|---|---|---|---|---|---|
| Berget.AI | Mistral | mistralai/Mistral-Small-3.2-24B-Instruct-2506 | 32,000 | 8,192 | $0.3365 / $0.3365 | Yes | Yes | Yes | Yes |
| Cortecs | Mistral | mistral-small-3.2-24b-instruct-2506 | 131,000 | 131,000 | $0.10 / $0.312 | No | Yes | Yes | No |
| Kilo Gateway | Mistral | mistralai/mistral-small-3.2-24b-instruct | 128,000 | 16,384 | $0.10 / $0.30 | No | Yes | Yes | Yes |
| NanoGPT | Mistral | mistralai/mistral-small-3.2-24b-instruct | 128,000 | 16,384 | $0.20 / $0.40 | No | No | No | Yes |
| OpenRouter | Mistral | mistralai/mistral-small-3.2-24b-instruct | 256,000 | 16,384 | $0.075 / $0.20 | No | Yes | Yes | Yes |
| OVHcloud AI Endpoints | Mistral | mistral-small-3.2-24b-instruct-2506 | 131,072 | 131,072 | $0.10 / $0.31 | No | Yes | Yes | Yes |
| Venice AI | Mistral | mistral-small-3-2-24b-instruct | 256,000 | 16,384 | $0.0938 / $0.25 | No | Yes | Yes | Yes |
| No rows match the current search. | |||||||||