Google logo

Gemma 4 31B

31B

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Input Price$0.20/1M tokens
Output Price$0.50/1M tokens
Intelligence29.4
Coding43.4

Specifications

Technical details and pricing.

ProviderGoogle
Context Window262,144 tokens
Release DateApr 2, 2026
ModalitiesText
CapabilitiesStructured Outputs, JSON Mode
AvailabilityChat, Inference API

Benchmarks

7 benchmark scores from Artificial Analysis.

GPQA85.7%
HLE22.7%
SciCode43.4%
LCR62.0%
IFBench75.6%
Tau259.9%
TerminalBench Hard36.4%

Composite Indices

Higher is better; speed and price are normalized

Standard Benchmarks

Only benchmarks with data are shown

Frequently Asked Questions

What is Gemma 4 31B good for?

Use Gemma 4 31B for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Gemma 4 31B cost?

Pricing is based on usage. Current rates are $0.20/1M tokens for input and $0.50/1M tokens for output.

Can I use Gemma 4 31B in LLMBase Chat?

Yes. Use the chat action on this page to open Gemma 4 31B in LLMBase Chat. Access still follows the current plan and model tier.

Does Gemma 4 31B support images or audio?

Gemma 4 31B focuses on text-based tasks.

Benchmarks and pricing use Artificial Analysis where available. Catalog specs are used as a fallback.