Skip to main content
GoogleApr 3, 2026

Google Gemma 4 31B Instruct

google-gemma-4-31b-itPrivateOpen weights

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.

$0.12/$0.36
per 1M in / out
256K
context window
16K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 58%86.9%
Blended pricecheaper than 94%$0.18
Context windowlarger than 22%256K
Max outputlarger than 8%16K

Further right is better. Hover a dot for its model.

Time to first token— 
Output speed— 
Uptime— 

Last 24 hours of Venice traffic.How it’s measured

Capabilities

What the model takes in, returns and supports through the API.

InTextImageVideo
OutText

Not supportedaudio input and X search

Benchmarks

GPQA Diamond
86.9%58th of 139 · DeepSeek V4 Flash 0423 scores higher for less

Specs

Model ID
google-gemma-4-31b-it
Endpoint
POST /api/v1/chat/completions
Context window
256,000 tokens
Max output
16,384 tokens
Reasoning
none · low · medium · high · default low
Precision
FP4
Privacy
Private
Added
Apr 3, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
Google Gemma 4 31B Instruct$0.12$0.3686.9%256K16K——
DeepSeek V4 Flash 0423$0.138$0.27587.4%1M256K——
GLM 4.7 Flash Heretic$0.07$0.4035.4%200K24K——
DeepSeek V4 Flash 0731$0.13$0.2686.4%1M256K——
GPT-6 Luna$0.10$0.5088.9%1.05M128K——

Other versions

  1. Google Gemma 3 27B InstructNov 2025
  2. Google Gemma 4 31B InstructApr 2026

Pricing

Billed per token in USD. Reasoning tokens bill as output.

Input$0.12per 1M tokens
Cached input$0.0925% off input
Output$0.36per 1M tokens

Estimate a workload

$0.0004per request
$4.20for 10,000 requests

Blended price against similar models

Google Gemma 4 31B Instruct$0.18

Per 1M tokens at three input tokens for each output token.

Quickstart

OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.

curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google-gemma-4-31b-it",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "low"
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelgoogle-gemma-4-31b-itRequired
messagestext · image_url · video_urlContent parts the model reads
max_completion_tokensUp to 16,384Counts reasoning tokens
reasoning_effortnone | low | medium | highDefault low
toolsFunction definitionsWith tool_choice
response_format{ type: "json_schema" }Output that matches a schema
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations
logprobstrue | falseWith top_logprobs