Mistral Devstral Small 2505
by NanoGPT · family devstral · listed Aug 2025
Mistral coding agent model for repository tasks and software engineering workflows
Current rates USD per 1M tokens
Input$0.06
Output$0.06
Cache read—
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
mistralai/Devstral-Small-2505- Context window
- 33K tokens
- Max output
- 8K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2025-08-02
- Last updated
- 2025-08-02
← All NanoGPT listings