Magistral Small 2506
by Nvidia · family magistral · listed Jun 2025W
Open Mistral reasoning model for transparent step-by-step problem solving
Current rates USD per 1M tokens
Inputfree
Outputfree
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
mistralai/magistral-small-2506- Context window
- 33K tokens
- Max output
- 33K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2025-06-10
- Last updated
- 2025-06-10
← All Nvidia listings