Novita

google/gemma-4-31b-it

google/gemma-4-31B-it
Context

256K

Input

text, image

Output

text

Tool calling

Supported

About this model

Gemma 4 31B is a state-of-the-art, open-weights multimodal dense model from Google DeepMind. It features a 256K token context window, excels at reasoning, coding, and agentic workflows, and supports interleaved text and image inputs.

Compare Text Models

Input modalities

text

Accepted as model input

image

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Novita
Available

Input tokens

$0.140 / 1M tokens

Output tokens

$0.400 / 1M tokens

Routing

OneInfer optimized

cerebras
Available

Input tokens

$0.990 / 1M tokens

Output tokens

$1.490 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$0.140 / 1M tokens
Output tokens$0.400 / 1M tokens

Performance

Published evaluation results associated with this model.

Reasoning

MMLU Pro85.2
GPQA Diamond85.7
AIME 202689.2

Vision

MMMU Pro76.9
MATH-Vision85.6

Coding

LiveCodeBench v680

API example

Refer Documentation
curl https://api.oneinfer.ai/v1/ula/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-31B-it",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'