← all models

Gemma 4 26B A4B

google · 4B active

openrouter free tier
Parameters 26B openrouter api · from the model id
Context 256K 262144 tokens
Input $0.08 OpenRouter
Output $0.26 OpenRouter
Cache read $0.04 OpenRouter

Accepts

image text video

Capabilities

frequency_penalty include_reasoning logit_bias logprobs max_completion_tokens max_tokens min_p presence_penalty reasoning repetition_penalty response_format seed stop structured_outputs temperature tool_choice tools top_k top_logprobs top_p

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...

The OpenRouter API truncates descriptions — read the full text at the source

Also known as

Every id and name this model has been seen under — for matching it against another catalogue.

openrouter google/gemma-4-26b-a4b-it huggingface google/gemma-4-26B-A4B-it version slug google/gemma-4-26b-a4b-it-20260403 name Google: Gemma 4 26B A4B display name Gemma 4 26B A4B

Identifiers

Vendor
google
OpenRouter
google/gemma-4-26b-a4b-it
Hugging Face
google/gemma-4-26B-A4B-it
Version slug
google/gemma-4-26b-a4b-it-20260403
Active parameters
4B
Released
2026-04-03T14:53:09.000Z
First seen
59 d ago
Last crawled
16 min ago