Googlegemma familyActive

Gemma 4 31B IT

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

JSONEmbed chartCompare
Context
262,144
Max output
32,768
Input / 1M
$0.14
Output / 1M
$0.40
Providers
3
01Profile

Profile

Released
2026-04-02
Last updated
2026-04-02
Knowledge cutoff
Weights
Open
02Capabilities

Capabilities

Input
text · image · video
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Attachments
Yes
Cache read
Cache write
03Pricing

Pricing across 2 providers

Per 1M tokens, USD. Sorted by input price. First-party row highlighted.

ProviderProvider model idInputOutputCache readContext
amazon-bedrockgoogle.gemma-4-31b$0.14$0.40Not listed262,144
neuralwattgemma-4-31b$0.14$0.42$0.01262,128
poegoogle/gemma-4-31bNot listedNot listedNot listed262,144
04History

Change history

7+ recent events since 2026-04-02

2026-09-10Addedamazon-bedrockoffering→ new
2026-09-06Removedcerebrasofferingremoved→ new
2026-07-30Addedneuralwattoffering→ new
2026-07-01Addedcerebrasoffering→ new
2026-04-07Addedpoeoffering→ new
2026-04-04Removedgoogleofferingremoved→ new
2026-04-03Addedgoogleoffering→ new
as of 2026-09-16
About ·Corrections ·Contact ·Privacy ·EN / 中文 / 繁體
HomeModelsLabsProvidersToolsRankingsChangesNews