GoogleApr 3, 2026
Google Gemma 4 31B Instruct
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
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
Streaming
Function callingstream: truetoolsStructured outputsresponse_formatReasoningreasoning_effort none · low · medium · highVisionUp to 10 imagesVideo inputVideo in messages
Web search
Prompt cachingReads at $0.09enable_web_searchLog probabilities
logprobsNot 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
- Weights
- google/gemma-4-31B-it
- Added
- Apr 3, 2026
Compare
| Model | Input | Output |
|---|---|---|
| Google Gemma 4 31B Instruct | $0.12 | $0.36 |
| DeepSeek V4 Flash 0423 | $0.138 | $0.275 |
| GLM 4.7 Flash Heretic | $0.07 | $0.40 |
| DeepSeek V4 Flash 0731 | $0.13 | $0.26 |
| GPT-6 Luna | $0.10 | $0.50 |
Other versions
- Google Gemma 3 27B InstructNov 2025
- 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
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/v1Parameters
| Parameter | Values |
|---|---|
model | google-gemma-4-31b-it |
messages | text · image_url · video_url |
max_completion_tokens | Up to 16,384 |
reasoning_effort | none | low | medium | high |
tools | Function definitions |
response_format | { type: |
stream | true | false |
venice_parameters.enable_web_search | auto | on | off |
logprobs | true | false |