VENICE ATLAS · MODEL DOSSIER · GOOGLE GEMMA 4 31B INSTRUCT

Model overview

Google Gemma 4 31B Instruct

Name: Google Gemma 4 31B Instruct
Brand: venice.ai
Price: 0.1200 USD
Availability: InStock

Gemma 4 31B is a dense model from Google DeepMind with 31B parameters, delivering frontier-level reasoning performance. It handles text, image, and video input, supports 256K context, function calling, and configurable thinking modes.

google-gemma-4-31b-it · venice.ai

Text · Venice catalog$0.12 per 1M tokensPrice on Venice AI

ModalityTextOn Venice AI

Primary price$0.12 per 1M tokensper 1M tokens

Context window256KMax tokens

Benchmarks12Benchmark results

Benchmark results

See the tests behind each score. They use the benchmark’s original scoring scale.

Finance#2026.31 rating Healthcare#2527.36 rating Language#1330.28 rating Legal#1526.31 rating Long Context#2416.42 rating

Agents1 result

t2-bencht2-bench · agents

86.4%

ReportedOct 2026

Healthcare1 result

MedXpertQAmedxpertqa · healthcare

61.3%

ReportedOct 2026

Language2 results

MMLU-Prommlu-pro · language

85.2%

ReportedOct 2026

MMMLUmmmlu · language

88.4%

ReportedOct 2026

Long Context1 result

MRCR v2 (8-needle)mrcr-v2-(8-needle) · long_context

66.4%

ReportedOct 2026

Math2 results

AIME 2026aime-2026 · math

89.2%

ReportedOct 2026

MathVisionmathvision · math

85.6%

ReportedOct 2026

Reasoning4 results

BIG-Bench Extra Hardbig-bench-extra-hard · reasoning

74.4%

ReportedOct 2026

GPQAgpqa · reasoning

84.3%

ReportedOct 2026

Humanity's Last Examhumanity's-last-exam · reasoning

26.5%

ReportedOct 2026

LiveCodeBench v6livecodebench-v6 · reasoning

80.0%

ReportedOct 2026

Vision1 result

MMMU-Prommmu-pro · vision

76.9%

ReportedOct 2026

Learn what each benchmark measures ↗

Pricing detail

Input price per 1M tokens: $0.12
Output price per 1M tokens: $0.36
Cache read price per 1M tokens: $0.0900
Blended price per 1M tokens (50/50): $0.24

Prices are published by Venice AI. Venice model page ↗

Capabilities

ReasoningFunction callingVisionVideo inputWeb search

Endpoint metadata

Privacy: private
Quantization: fp4
Maximum completion tokens: 8K
Uncensored: No
Beta: No
Mapping confidence: 100.0%

View model source ↗

All capabilities

Max Images: 10
Quantization: fp4
Supports E2 E E: No
Supports Vision: Yes
Supports X Search: No
Optimized For Code: No
Supports Log Probs: Yes
Supports Reasoning: Yes
Supports Web Search: Yes
Supports Audio Input: No
Supports Video Input: Yes
Default Reasoning Effort: low
Reasoning Effort Options: none, low, medium, high
Supports Multiple Images: Yes
Supports Response Schema: Yes
Supports Tee Attestation: No
Supports Function Calling: Yes
Supports Reasoning Effort: Yes

Related models

More from google

gemini-3-8-flashGemini 3.8 Flash$0.94 input per 1M tokens ↗gemini-4-argonGemini 4 Argon$2.50 input per 1M tokens ↗google-gemma-3-27b-itGoogle Gemma 3 27B Instruct$0.12 input per 1M tokens ↗