# Mistral Medium 3 API prices

Mistral Medium 3 (mistral-medium) — 131k context, 131k max output.
8 metered per-token offers from 9 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Azure | $0.4 | $2 | — | 128k |
| Azure Cognitive Services | $0.4 | $2 | — | 128k |
| Eden AI | $0.4 | $2 | — | 131k |
| Merge Gateway | $0.4 | $2 | $0.04 | 128k |
| Mistral | $0.4 | $2 | — | 131k |
| NanoGPT | $0.4 | $2 | $0.2 | 131k |
| OpenRouter | $0.4 | $2 | $0.04 | 131k |
| Pioneer | $0.4 | $2 | $0.4 | 128k |

## Summary

- Cheapest input: $0.4 per 1M tokens (Azure)
- Cheapest output: $2 per 1M tokens (Azure)
- First-party: $2 per 1M output tokens (Mistral)
- Free offers: Nvidia
- Subscription plans (not per-token): none
- Released: 2025-05-07
- Inputs: image, pdf, text

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