# Gemma 4 31B Instruct API prices

Gemma 4 31B Instruct (gemma) — 256k context, 8k 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 |
| --- | --- | --- | --- | --- |
| Venice AI | $0.12 | $0.36 | $0.09 | 256k |
| Berget.AI | $0.275 | $0.55 | — | 128k |

## Summary

- Cheapest input: $0.12 per 1M tokens (Venice AI)
- Cheapest output: $0.36 per 1M tokens (Venice AI)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-04-02
- Inputs: audio, image, text, video

## FAQ

### What is the cheapest Gemma 4 31B Instruct API?

As of Oct 4, 2026, Venice AI has the lowest Gemma 4 31B Instruct output price at $0.36 per 1M tokens, and Venice AI has the lowest input price at $0.12 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Gemma 4 31B Instruct?

2 providers list Gemma 4 31B Instruct on Sovyron; 2 of them sell it at a metered per-token price.

### Is Gemma 4 31B Instruct free?

No provider in the Sovyron catalog lists a free tier for Gemma 4 31B Instruct.

### What is the context window of Gemma 4 31B Instruct?

Gemma 4 31B Instruct supports a 256k-token context window and up to 8k output tokens.

HTML page: https://sovyron.com/models/gemma-4-31b-instruct/
Full dataset: https://sovyron.com/data/catalog.json