Google Gemma 4 31B Instruct API: Pricing and Specs

Google Gemma 4 31B Instruct API

Google Gemma 4 31B Instruct is a large language model by Google, available on the Venice API as google-gemma-4-31b-it. It runs privately, with zero data retention.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 Instruct API pricing

Model ID	Variant	Privacy	Price
`google-gemma-4-31b-it`	Standard	Private	$0.12 / $0.36 per 1M

Google Gemma 4 31B Instruct specifications

Spec	Value
Provider	Google
Released	Apr 3, 2026
Privacy	Private
Status	Stable
Open weights	Yes
Context window	256K tokens
Max output	16K tokens
Reasoning effort	none, low, medium, high
Served precision	FP4

How to use the Google Gemma 4 31B Instruct API

Send requests to POST https://api.venice.ai/api/v1/chat/completions with "model": "google-gemma-4-31b-it" and your 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"
  }'

Related models

Google Gemma 3 27B Instruct API: $0.12 / $0.20 per 1M
DeepSeek V4 Flash 0423 API: $0.138 / $0.275 per 1M
GLM 4.7 Flash Heretic API: $0.07 / $0.40 per 1M
DeepSeek V4 Flash 0731 API: $0.13 / $0.26 per 1M
GPT-6 Luna API: $0.10 / $0.50 per 1M

Explore

By modality