Mistral Small 3.1 24B
by Vertex · family mistral-small · listed Mar 2025TVW
Efficient multimodal model for instruction following, coding, reasoning, and function calling
Current rates USD per 1M tokens
Input$0.10
Output$0.30
Cache read—
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
mistral-small-2503- Context window
- 128K tokens
- Max output
- 16K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Jun 2024
- Released
- 2025-03-17
- Last updated
- 2025-03-17
← All Vertex listings