# Mistral Small 4 API prices

Mistral Small 4 (mistral-small) — 262k context, 256k max output.
13 metered per-token offers from 12 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Cortecs | $0.143 | $0.568 | $0.014 | 262k |
| Eden AI | $0.15 | $0.6 | $0.015 | 262k |
| EmpirioLabs AI | $0.15 | $0.6 | $0.15 | 256k |
| Kilo Gateway | $0.15 | $0.6 | $0.015 | 262k |
| Mistral | $0.15 | $0.6 | — | 256k |
| OpenRouter | $0.15 | $0.6 | $0.015 | 262k |
| Opper | $0.15 | $0.6 | — | 256k |
| Pioneer | $0.15 | $0.6 | $0.015 | 32k |
| Requesty | $0.165 | $0.66 | $0.165 | 256k |
| Requesty (eu) | $0.165 | $0.66 | $0.165 | 256k |
| AKI.IO | $0.2 | $0.6 | — | 262k |
| Venice AI | $0.1875 | $0.75 | — | 256k |
| Infomaniak | $0.25 | $0.93 | — | 256k |

## Summary

- Cheapest input: $0.143 per 1M tokens (Cortecs)
- Cheapest output: $0.568 per 1M tokens (Cortecs)
- First-party: $0.6 per 1M output tokens (Mistral)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-03-16
- Inputs: image, text

HTML page: https://llmprice.gitlab.io/models/mistral-small-4/
Full dataset: https://llmprice.gitlab.io/data/catalog.json