Skip to main content
Prime Intellect logo

Gemma 4 31B API pricing on Prime Intellect

Every Prime Intellect Gemma 4 31B rate we track, compared against 16 providers serving the same model.

Input from /1M
$0.200
Output /1M
$0.335
Input price rank
#7 of 16
Last updated
November 21, 2026

The cheapest Gemma 4 31B input price we currently track is $0.070/1M on OpenRelay.

The cheapest Gemma 4 31B output price is $0.300/1M on OpenRelay.

Prime Intellect Gemma 4 31B rates

Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.

Prime Intellect Gemma 4 31B pricing by mode
ModeInputOutput
Standard$0.200/1M$0.335/1M

About Gemma 4 31B

Creator
Google
Context
262K
Modalities
text, image, video
Open weights
Yes
Full Gemma 4 31B details and every provider →Compare API pricing for every Gemma model →

Gemma 4 31B on other providers

About Prime Intellect

Prime Intellect is an AI research company and compute platform. It aggregates on-demand GPUs and reserved clusters from many providers behind one account, and runs Prime Intellect Inference, an OpenAI-compatible API that serves open-weight models directly and routes to proprietary models, plus hosted reinforcement-learning training through its Lab platform.

Frequently Asked Questions

How much does Gemma 4 31B cost on Prime Intellect?

Prime Intellect serves Gemma 4 31B from $0.200 per 1M input tokens, across 1 tracked pricing mode. Prices are collected daily — see the table above for current input, output, and cached-input rates.

Is Prime Intellect the cheapest way to run Gemma 4 31B?

Prime Intellect ranks #7 of 16 providers we track serving Gemma 4 31B on input price. The cheapest input price right now is on OpenRelay. The lowest output price is $0.300/1M on OpenRelay. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.

Does Prime Intellect offer batch or cached pricing for Gemma 4 31B?

We track 1 Gemma 4 31B offering from Prime Intellect. Batch and cached-input rates appear in the table above when the provider publishes them; blank cells mean we have no current figure for that mode.