onomeoonomeoBeta

gemini-3.8-flash vs gemma-4-31b

gemini-3.8-flash
1 advantage
gemma-4-31b
3 advantages

How to choose

gemini-3.8-flashLonger context: 1M tokens
gemma-4-31bReads imagesNo training on conversationsOpen weights

gemini-3.8-flash

By Google

gemma-4-31b

By GoogleNew in the last two weeks

Where they differ

gemini-3.8-flashgemma-4-31b
On this site
—Availability, last 3 days98%102 calls
—Availability, this week's tests96%193 tests
—Average response this week2.1s
$5.63Reference price per million output tokensFree
UnrankedPlace in this week's ranking#8
$1.13Reference price per million input tokensFree
The model itself
1M tokensContext length256K tokens
64K tokensLongest reply256K tokens
NoReads imagesYes
Used to train and improve the provider’s models.Conversations used for trainingNot used for training.
Not publishedKnowledge cutoffJan 2025
2 Sep 2026Released2 Apr 2026
NoOpen weightsYes
$0.11Reference price per million cache-read tokensFree

Where they match

  • Calls toolsYes
  • Thinks before answeringYes

Availability over 3 days counts every call made through the site; this week's availability counts every call over the last 7 days, scheduled tests included, and response time comes from the site's own scheduled tests. Models marked as free are counted in calls; paid models are charged by usage, in US dollars.

Compare next

Figures come from real calls made through this site. Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.