mistral-small-3.1-24b-instruct
mistralai
Building upon Mistral Small 3 (2501), Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance. With 24 billion parameters, this model achieves top-tier capabilities in both text and vision tasks.
- Context window
- 128,000 tokens
- Input cost
- $0.35 / 1M
- Output cost
- $0.56 / 1M
- Latency (p50)
- —