Gemma 4 26B-A4B

google • gemma-4-26b-a4b-it

Model Information

Slug	gemma-4-26b-a4b-it
LLM.txt	View
Release Date	April 2, 2026 New
HLE	0.172
GPQA	0.823

Organization

Name	google
Website	https://gemini.google.com/

Model Description

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 a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.

Available at 9 Providers

Provider	Type	Model Name	Original Model	Input ($/1M)	Output ($/1M)	Actions
Novita AI		gemma-4-26b-a4b-it	`google/gemma-4-26b-a4b-it`	$0.13	$0.40	Visit
Parasail		Gemma 4 26b A4b It	`parasail-gemma-4-26b-a4b-it`	$0.13	$0.40	Model
Kilo Code	Code	Google: Gemma 4 26B A4B	`google/gemma-4-26b-a4b-it`	$0.13	$0.40	Model
OpenRouter	Chat Code	Gemma 4 26B A4B	`google/gemma-4-26b-a4b-it`	$0.13	$0.40	Model
GMI Cloud		Gemma 4 26B A4B	`google/gemma-4-26b-a4b-it`	$0.13	$0.40	Visit
AIHubMix		gemma-4-26b-a4b-it	`gemma-4-26b-a4b-it`	$0.14	$0.40	Model
Nano-GPT		Gemma 4 26B A4B	`google/gemma-4-26b-a4b-it`	-	-	Visit
Nano-GPT		Gemma 4 26B A4B Thinking	`google/gemma-4-26b-a4b-it:thinking`	-	-	Visit
Writingmate	Chat Code	Google: Gemma 4 26B A4B	`google/gemma-4-26b-a4b-it`	-	-	Model

Back to Models View Organization