Gemma 4 31B

31B

Gemma 4 31B is engineered to tackle the most demanding enterprise workloads and complex reasoning tasks.

Context
262K
Max output
131K
Input price
$0.14/1M tokens
Output price
$0.4/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming

Details

Model IDgoogle/gemma-4-31b-it
Provider Novita AI
Creator Google AI
Familygemma-4
License—
Statusactive
Typechat
Input modalitiestext, image
Output modalitiestext
Open weight—
Parameters31B
Architecture—
Context window262K tokens
Max input—
Max output131K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.novita.ai/v3/openai/v1/chat/completions

Pricing

Input
$0.14
Output
$0.4
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: gemma-4

ModelContextMax outPricing
Gemma 4 26B A4B262K131K$0.13$0.4
Gemma 4 31B262K131K$0.14$0.4

API

GET/v1/models/novita/google/gemma-4-31b-it