Mistral: Small 4
Fast Mistral production model for chat, extraction, and cost-sensitive agents
Price changes
Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.
- ↑ higherOutput $0.3 → $0.6
- ↑ higherInput $0.075 → $0.15
- ↓ lowerOutput $0.568 → $0.3
- ↓ lowerInput $0.143 → $0.075
- ↓ lowerOutput $0.6 → $0.568
- ↓ lowerInput $0.15 → $0.143
Sources
Same model, different sources. Our first-party rate is listed first, then 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.devcheapestmistralai/mistral-small-2603 | Kilo Gateway | $0.15 | $0.6 | $0.015 | 262K |
| OpenRoutermistralai/mistral-small-2603 | OpenRouter | $0.15 | $0.6 | $0.015 | 262K |
| models.devmistral-small-2603 | DevPass (LLM Gateway) | $0.15 | $0.6 | $0 | 262K |
| models.devmistral/mistral-small-2603 | Eden AI | $0.15 | $0.6 | $0.015 | 262K |
| models.devmistral/mistral-small-2603 | LLM Gateway | $0.15 | $0.6 | $0 | 262K |
| models.devmistral-small-2603 | Mistral | $0.15 | $0.6 | $0.015 | 262K |
| models.devmistral/mistral-small-2603 | Tempr Gateway | $0.15 | $0.6 | $0.015 | 256K |
| LiteLLMmistral-small-2603 | N/A | $0.15 | $0.6 | $0.015 | N/A |
| models.devmistral-small-2603 | Cortecs | $0.156 | $0.625 | $0.016 | 262K |
| models.devauto/mistralai/mistral-small-2603 | LowRouter | $0.1569 | $0.6275 | $0.0157 | 256K |
| models.devmistralai/mistral-small-2603 | Prime Inference | $0.165 | $0.66 | $0 | 262K |
| models.devmistral-small-2603 | Requesty | $0.165 | $0.66 | $0.165 | 256K |
| models.devmistralai/mistral-small-2603 | AI/ML API | $0.1984 | $0.7935 | $0.0159 | 262K |
| models.devmistral-small-2603 | Opper | $0.5811 | $2.44 | $0 | 256K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- In: pdf
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence11.3i
- AA coding26.6i
- AA agentic0.8i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.