gemma-4-31B-it-Ultra

gemma

Ultra speed version of gemma-4-31B-it

Context
131K
Input price
$0.27/1M tokens
Output price
$0.76/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
JSON Mode
Infrastructure
Streaming
Fine-tuning

Details

Provider DeepInfra
Creator Google AI
Familygemma-4
Licensegemma
Statusactive
Typechat
Input modalitiestext, image
Output modalitiestext
Open weightNo
Parameters—
Architecture—
Context window131K tokens
Max input—
Max output—
Reasoning tokensYes
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.deepinfra.com/v1/openai/v1/chat/completions

Pricing

Input
$0.27
Output
$0.76
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: gemma-4

ModelContextMax outPricing
gemma-4-E4B-it131K—$0.02$0.1
gemma-4-26B-A4B-it262K—$0.07$0.34
gemma-4-31B-it-turbo262K—$0.09$0.34
gemma-4-31B-it262K—$0.2$0.4
gemma-4-31B-it-Ultra131K—$0.27$0.76

API

GET/v1/models/deepinfra/google/gemma-4-31B-it-Ultra

gemma-4-31B-it-Ultra

Ultra speed version of gemma-4-31B-it

Changes · 2 entries
google/gemma-4-31B-it-Ultracreateca7a400Nov 2, 2026, 03:02 AM
google/gemma-4-31B-it-Ultracreatedbe2d73Jul 31, 2026, 06:07 AM