Skip to main content
Models/Google/Gemma 4 31B

Gemma 4 31B

Google 🧠 Language Model

Google's open-weight dense model with 262K context and strong multilingual reasoning

Specifications

Input modalitiestext
Output modalitiestext
Capabilitiestools, reasoning
Relative speed●●●●○ Fast
Context window262,144 tokens
Max output32,768 tokens
Vision inputNo
Tool callingYes
Streaming outputYes
Input price$0.245 / 1M
Output price$0.7 / 1M

Pricing

$0.245 / 1M input tokens  ·  $0.7 / 1M output tokens

Platform credit pricing — live rates on the Models page.

Use Gemma 4 31B on Zubnet →

More from Google

G
Gemini 3 Pro
Google's most capable reasoning model with 1M context window and multimodal support
🧠 Language Model
G
Gemini Omni Flash
Google's omni-modal Flash — fast conversational generation across modalities
🧠 Language Model
G
Gemini 3 Flash
Google's fastest frontier model. Beats 2.5 Pro at 1/4 the cost with 1M context
🧠 Language Model
G
Gemini 2.5 Flash
Fast and efficient model with adaptive thinking for complex tasks
🧠 Language Model