# Mistral: Saba API prices

Mistral: Saba (mistral) — 33k context, 26k max output.
2 metered per-token offers from 2 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| NanoGPT | $0.1989 | $0.595 | $0.0994 | 33k |
| Kilo Gateway | $0.2 | $0.6 | $0.02 | 33k |

## Summary

- Cheapest input: $0.1989 per 1M tokens (NanoGPT)
- Cheapest output: $0.595 per 1M tokens (NanoGPT)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2024-01-01
- Inputs: pdf, text

## FAQ

### What is the cheapest Mistral: Saba API?

As of Oct 4, 2026, NanoGPT has the lowest Mistral: Saba output price at $0.595 per 1M tokens, and NanoGPT has the lowest input price at $0.1989 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Mistral: Saba?

2 providers list Mistral: Saba on Sovyron; 2 of them sell it at a metered per-token price.

### Is Mistral: Saba free?

No provider in the Sovyron catalog lists a free tier for Mistral: Saba.

### What is the context window of Mistral: Saba?

Mistral: Saba supports a 33k-token context window and up to 26k output tokens.

HTML page: https://sovyron.com/models/mistral-saba/
Full dataset: https://sovyron.com/data/catalog.json