Mistral Small 4
Fast Mistral production model for chat, extraction, and cost-sensitive agents
Cheapest input
$0.15
$/MTok · models.dev
Cheapest output
$0.6
$/MTok
Context
256K
tokens
Offers
2
1 source
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestmistral-small-2603 | Mistral | $0.15 | $0.6 | $0 | 256K |
| models.devmistral-small-2603 | Venice AI | $0.1875 | $0.75 | $0 | 256K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- Out: text
Knowledge cutoff: 2025-06Released: 2026-03-16Family: mistral-small
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence19.6
- AA coding26.6
- AA agentic4.7
Sources: Arena AI, Artificial Analysis. See /benchmarks.