Model decision page
GGoogle: Gemma 4 31B

Google: Gemma 4 31B

Context Window: 262.1K
Max Output Tokens: 262.1K
LLM

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...

Last verified
7/7/2026, 11:49:41 PM
Confidence
We prioritize official prices and captured reseller prices. Always confirm once again before purchasing.
Lowest verified entry
OpenRouter
Verified
$0.12 / $0.35

Not enough reseller data

Compare next
OpenRouter
Verified
$0.12 / $0.35

Price is competitive; compare source freshness and platform rules before choosing.

Official baseline
Google: Gemma 4 31B
¥1.2e-7 / ¥3.5e-7

Use this baseline before choosing a reseller.

Monthly cost calculator

Official
Google: Gemma 4 31B
¥1.9e-6
Lowest
OpenRouter
¥13.68
Compare next
OpenRouter
¥13.68

Estimated from current per-1M token prices; excludes cache, concurrency, package discounts, and platform rules.

Price Overview

Budget
Google: Gemma 4 31BOfficial
¥1.2e-7/¥3.5e-7
OpenRouter
$0.12/$0.35
Input Price
Output Price
Unit: per 1M tokens

Platform Price Comparison

per 1M tokens
PlatformInput Price / 1M tokensOutput Price / 1M tokensSavings
OROpenRouter
Best Deal
Verified
Global multi-model routing and pricing platform
$0.12
$0.35
-
Google: Gemma 4 31B
Official
Base Price
¥1.2e-7
¥3.5e-7
--

Prices and information displayed are sourced from publicly available channels and are for reference only. They do not constitute any purchasing advice. Inclusion does not imply recommendation, endorsement, or guarantee of the services or products listed. We assume no legal liability for any consequences arising from the use of this information.