# Mistral Small 3.2 24B Instruct API prices

Mistral Small 3.2 24B Instruct (mistral-small) — 256k context, 33k max output.
3 metered per-token offers from 4 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Venice AI | $0.0938 | $0.25 | — | 256k |
| Scaleway | $0.15 | $0.35 | — | 128k |
| NanoGPT | $0.2 | $0.4 | $0.1 | 128k |

## Summary

- Cheapest input: $0.0938 per 1M tokens (Venice AI)
- Cheapest output: $0.25 per 1M tokens (Venice AI)
- First-party: not listed separately
- Free offers: Meganova
- Subscription plans (not per-token): none
- Released: 2025-06-20
- Inputs: image, text

HTML page: https://llmprice.gitlab.io/models/mistral-small-3-2-24b-instruct/
Full dataset: https://llmprice.gitlab.io/data/catalog.json