Devstral Small 2
Mistral AI's compact Devstral coding model via the Vercel AI Gateway: fast, low-cost code generation and editing with function calling at a 256k context window. Available at the base tier. Uses 1 base request per send before length multipliers. Does not support web search or image input.
You always get the exact model you pick — we never silently route you to another.
About Devstral Small 2
Devstral Small 2 is the compact, low-cost member of Mistral's Devstral coding family, served on just4o.chat through the Vercel AI Gateway as mistral/devstral-small-2. At $0.10 per million input and $0.30 per million output tokens, it is one of the cheapest capable coding models available here, which makes it well suited to high-volume or budget-sensitive workflows — bulk code generation, quick edits, scaffolding, and anything where you would rather not spend flagship rates. It keeps the family's practical strengths: a 256k-token context window for working across larger files, and function calling for tool-driven tasks. On just4o.chat it is a base-tier model on every plan, billed at just 1 base request per send before length multipliers. The trade-offs are the expected ones for a small model: it is text-only with no native web search, and it will not match the depth of Devstral 2 or a frontier model on the hardest engineering problems. For fast, affordable, everyday coding help at scale, though, it is hard to beat on price.
Best for
- High-volume code generation where per-request cost matters
- Quick edits, boilerplate, and scaffolding tasks
- Test generation and routine refactors
- Tool-using coding workflows on a budget
- Working across larger files with the 256k context window
Specifications
| Provider | Mistral |
|---|---|
| Released | 2025-12 |
| Intelligence | Medium |
| Speed | Fast |
| Context window | 256,000 tokens |
| Knowledge cutoff | Not officially published |
| Input price | $0.10 / 1M tokens |
| Output price | $0.30 / 1M tokens |
| Request cost | 1 base request |
| Plan tier | Base |
| Input | Text |
| Output | Text |
| Features | 1 base request per send before length multipliers, Function calling supported, Low-cost coding workhorse, Served through the Vercel AI Gateway (mistral/devstral-small-2), Mistral applies zero data retention to gateway traffic |
| Model ID | devstral-small-2 |
Frequently asked questions
$0.10 per million input tokens and $0.30 per million output tokens at provider reference pricing — among the lowest-cost coding models on just4o.chat. It uses just 1 base request per send before length multipliers.
Through the Vercel AI Gateway's OpenAI-compatible endpoint under the mistral/devstral-small-2 route. Mistral applies zero data retention to gateway traffic.
256,000 tokens, the same as the larger Devstral 2.
No. It is text-only with no native web search, built for coding tasks rather than research.
For the hardest multi-step engineering tasks where depth matters. Devstral Small 2 is the better pick for speed, scale, and cost on routine coding work.