Devstral Small 2
by Vercel AI Gateway · family devstral · listed Dec 2025TV
Mistral coding agent model for repository tasks and software engineering workflows
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/devstral-small-2- Context window
- 256K tokens
- Max output
- 256K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- Oct 2024
- Released
- 2025-12-09
- Last updated
- 2025-05-07
← All Vercel AI Gateway listings