Gemma by Google

Model family · Model APIs & inference · indexed, not reviewed

on OpenRouter

Not reviewed

No score, grade or rank. This listing is facts from OpenRouter and our own checks, and it stays out of the rankings until the panel reviews it.

How the index works

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
What OpenRouter says about Gemma 4 26B A4B

Facts

Maker: Google
Models: 6 on OpenRouter
Newest: google/gemma-4-26b-a4b-it

From OpenRouter and our own checks. JSON · Markdown

Why it's listed

OpenRouter lists it, with prices from the providers that serve it.

Being indexed says nothing about quality, and nobody can pay for it. Is this yours? Ask for a review.

Models 6

Model	Released	Context	Input / 1M	Output / 1M	Supports
Gemma 4 26B A4B `google/gemma-4-26b-a4b-it`	Apr 2026	262k	$0.0675	$0.225	tools, structured output, reasoning, caching, image, video, free variant
Gemma 4 31B `google/gemma-4-31b-it`	Apr 2026	262k	$0.09	$0.34	tools, structured output, reasoning, caching, image, video, free variant
Gemma 3 4B `google/gemma-3-4b-it`	Mar 2025	131k	$0.05	$0.10	structured output, image
Gemma 3 12B `google/gemma-3-12b-it`	Mar 2025	131k	$0.05	$0.15	tools, structured output, image
Gemma 3 27B `google/gemma-3-27b-it`	Mar 2025	131k	$0.08	$0.45	tools, structured output, caching, image
Gemma 2 27B `google/gemma-2-27b-it`	Jul 2024	8k	$0.65	$0.65	structured output

Prices and limits as OpenRouter lists them, in dollars per million tokens; a provider's own price can differ.

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.