Gemma 4 31B

Google · Mid

Compare →

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 / 1M

$0.12

Output / 1M

$0.35

Cached input / 1M

$0.09

Context window

262K

Where it sits

60th-cheapest mid model

by blended $/Mtok among 262 listed mid models

69% below the mid median

blended $/Mtok across 262 mid models

Output costs 2.9× input

$0.12 in / $0.35 out per 1M

Cached input saves 25%

$0.09 vs $0.12 per 1M fresh

Held flat since launch (Jun 2026)

no blended price change recorded

Computed live from current prices and this model's history — not hand-written, so it stays accurate as prices move.

Price history

Only one price on record so far — the history chart appears once a price changes.

Snapshots

Effective Input Output Cached in Note Source
11 Jun 2026 $0.12 $0.35 $0.09 Imported from OpenRouter openrouter.ai

More from Google