# Mistral Medium 3.5 API prices

Mistral Medium 3.5 (mistral-medium) — 262k context, 262k max output.
9 metered per-token offers from 12 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Cortecs | $1.393 | $7.13 | $0.139 | 256k |
| Eden AI | $1.5 | $7.5 | $0.15 | 262k |
| Mistral | $1.5 | $7.5 | — | 262k |
| NanoGPT | $1.5 | $7.5 | $0.75 | 256k |
| OpenRouter | $1.5 | $7.5 | — | 262k |
| Pioneer | $1.5 | $7.5 | $1.5 | 256k |
| evroc | $1.725 | $6.9 | — | 262k |
| Requesty | $1.65 | $8.25 | $1.65 | 262k |
| GreenPT | $2.052 | $10.26 | — | 262k |

## Summary

- Cheapest input: $1.393 per 1M tokens (Cortecs)
- Cheapest output: $6.9 per 1M tokens (evroc)
- First-party: $7.5 per 1M output tokens (Mistral)
- Free offers: Kenari, Nvidia
- Subscription plans (not per-token): none
- Released: 2026-04-29
- Inputs: image, pdf, text

HTML page: https://llmprice.gitlab.io/models/mistral-medium-3-5/
Full dataset: https://llmprice.gitlab.io/data/catalog.json