Gemma 4 31B pricing
$ Affordable$0.12/M input · $0.35/M output. List prices from provider data; in idapt, chat is metered per token with transparent, usage-based pricing at the prices shown in the app.
Full rate table
| Rate | Price | Unit |
|---|---|---|
| Input | 0.12 | /M tokens |
| Output | 0.35 | /M tokens |
| Cache read | 0.09 | /M tokens |
What typical work costs
| Workload | Tokens | List price |
|---|---|---|
| Quick question | 1K tokens in, 500 out | $0.0003 |
| Long-document summary | 60K tokens in, 2K out | $0.0079 |
| Agent working session | 400K tokens in, 40K out across a day | $0.06 |
Price your own workload
- Per call
- $0.0003
- Per month
- $0.03
Compare up to four models at once in the cost calculator.
Frequently asked
What does Gemma 4 31B cost per 1M tokens?
Gemma 4 31B lists at $0.12 per 1M input tokens and $0.35 per 1M output tokens.
Does Gemma 4 31B discount cached input tokens?
Yes. Cached input tokens are billed at $0.09 per 1M, versus $0.12 for fresh input. Prompts that repeat a long prefix (a system prompt, attached files) benefit the most.
What does a typical chat message with Gemma 4 31B cost?
A message with about 1,000 input tokens and a 500-token reply costs roughly $0.0003 at list price. Long documents and long replies scale that linearly with token counts.
Is Gemma 4 31B cheaper than Gemma 4 26B A4B?
Gemma 4 26B A4B has the lower blended price at a 3:1 input:output mix. Gemma 4 31B: $0.12 in / $0.35 out per 1M. Gemma 4 26B A4B: $0.06 in / $0.33 out per 1M.
How does idapt bill Gemma 4 31B?
Gemma 4 31B is in idapt's free lane: signed-in users run it against the free daily allowance, with transparent, usage-based pricing beyond it at the prices shown in the app.
Part of the Gemma 4 31B model page · run it locally · cheapest models board · price changes