Gemma 3 12B API pricing on Runcrate
Every Runcrate Gemma 3 12B rate we track, compared against 7 providers serving the same model.
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.
| Mode | Input | Output |
|---|---|---|
| Standard | $0.052/1M | $0.158/1M |
About Gemma 3 12B
- Creator
- Context
- 131K
- Modalities
- text, image
- Open weights
- Yes
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.