Gemma 4 31B API pricing on GMI Cloud
Every GMI Cloud Gemma 4 31B rate we track, compared against 9 providers serving the same model.
The cheapest Gemma 4 31B input price we currently track is $0.090/1M on Deep Infra.
The cheapest Gemma 4 31B output price is $0.340/1M on Deep Infra.
GMI Cloud Gemma 4 31B rates
Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.
| Mode | Input | Output |
|---|---|---|
| Standard | $0.140/1M | $0.400/1M |
About Gemma 4 31B
- Creator
- Context
- 262K
- Modalities
- text, image, video
- Open weights
- Yes
Gemma 4 31B on other providers
About GMI Cloud
GMI Cloud is a neocloud combining dedicated NVIDIA GPU compute (H100, H200, B200, GB200, with GB300 on pre-order) and a serverless, OpenAI-compatible inference API for text, image, video, and audio models.
Frequently Asked Questions
How much does Gemma 4 31B cost on GMI Cloud?
GMI Cloud serves Gemma 4 31B from $0.140 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 GMI Cloud the cheapest way to run Gemma 4 31B?
GMI Cloud ranks #3 of 9 providers we track serving Gemma 4 31B on input price. The cheapest input price right now is on Deep Infra. The lowest output price is $0.340/1M on Deep Infra. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.
Does GMI Cloud offer batch or cached pricing for Gemma 4 31B?
We track 1 Gemma 4 31B offering from GMI Cloud. 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.