Skip to main content
Runcrate logo

Gemma 3 12B API pricing on Runcrate

Every Runcrate Gemma 3 12B rate we track, compared against 7 providers serving the same model.

Input from /1M
$0.052
Output /1M
$0.158
Input price rank
#4 of 7
Last updated
November 21, 2026

The cheapest Gemma 3 12B input price we currently track is $0.050/1M on Deep Infra.

The cheapest Gemma 3 12B output price is $0.100/1M on Novita AI.

Runcrate Gemma 3 12B rates

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

Runcrate Gemma 3 12B pricing by mode
ModeInputOutput
Standard$0.052/1M$0.158/1M

About Gemma 3 12B

Creator
Google
Context
131K
Modalities
text, image
Open weights
Yes
Full Gemma 3 12B details and every provider →Compare API pricing for every Gemma model →

Gemma 3 12B on other providers

About Runcrate

Runcrate runs a token-billed inference API over a catalog of open-source text, image, video, audio and embedding models alongside on-demand GPU instances and reserved clusters, billed from a single credit balance. It is operated by Aeonmind, LLC.

Frequently Asked Questions

How much does Gemma 3 12B cost on Runcrate?

Runcrate serves Gemma 3 12B from $0.052 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 Runcrate the cheapest way to run Gemma 3 12B?

Runcrate ranks #4 of 7 providers we track serving Gemma 3 12B on input price. The cheapest input price right now is on Deep Infra. The lowest output price is $0.100/1M on Novita AI. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.

Does Runcrate offer batch or cached pricing for Gemma 3 12B?

We track 1 Gemma 3 12B offering from Runcrate. 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.