Skip to main content
Heabsy logo

Gemma 4 31B API pricing on Heabsy

Every Heabsy Gemma 4 31B rate we track, compared against 12 providers serving the same model.

Input from /1M
$0.140
Output /1M
$0.520
Price rank
#5 of 12
Last updated
September 30, 2026

The cheapest Gemma 4 31B input price we currently track is $0.090/1M on Deep Infra.

Heabsy Gemma 4 31B rates

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

Heabsy Gemma 4 31B pricing by mode
ModeInputOutput
Standard$0.140/1M$0.520/1M

About Gemma 4 31B

Creator
Google
Context
262K
Modalities
text, image, video
Full Gemma 4 31B details and every provider →

Gemma 4 31B on other providers

About Heabsy

Heabsy is an OpenAI- and Anthropic-compatible inference API for open-weight models, operated by FEYA, s.r.o. in Bratislava, Slovakia, an EU company with no US parent. Models in the EEA tier, including Qwen3.8 27B, run on GPUs that Heabsy owns and operates inside the European Economic Area, with zero data retention: prompts and completions are processed in memory and never written to logs. A routed tier adds more than 25 open models (DeepSeek, Kimi, GLM, gpt-oss, Llama, Gemma, Qwen and others) bought from global providers under a European contract; every model in the catalog is labelled with where it is processed. One API key, one EU invoice, per-token pricing with no minimum spend or subscription.

Frequently Asked Questions

How much does Gemma 4 31B cost on Heabsy?

Heabsy 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 Heabsy the cheapest way to run Gemma 4 31B?

Heabsy ranks #5 of 12 providers we track serving Gemma 4 31B. The cheapest input price right now is on Deep Infra. Price is only one factor — throughput, latency, and context limits differ between providers.

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

We track 1 Gemma 4 31B offering from Heabsy. 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.