Gemma 4 26B A4B

Google· released 3 Apr 2026

google/gemma-4-26b-a4b-it

Input / 1M tokens: $0.068
Output / 1M tokens: $0.225

Context window262K tokens

Longest answer: 236K tokens

reads imagereads textreads videoopen weightstool callingvisionreasoning

About

Gemma 4 26B A4B is Google’s instruction-tuned Mixture-of-Experts model from Google DeepMind. It has 25.2 billion total parameters, while 3.8 billion activate for each inference token. The listed summary describes quality near a 31B model at that activation level. Gemma 4 26B A4B accepts text, images, and video, and produces text. It supports tools, vision, and reasoning, with a 262,144-token context window and a maximum output of 235,929 tokens. Google lists the model as open weights, with the Hugging Face identifier google/gemma-4-26B-A4B-it. Its model ID is google/gemma-4-26b-a4b-it, and its official page is on OpenRouter. Released and created on April 3, 2026, it is priced at $0.0675 per 1 million input tokens and $0.225 per 1 million output tokens.

Who it is for

It suits builders needing an open-weights model that handles text, images, and video. Teams can use its tool support, vision, reasoning, and large context window where those inputs fit their stack.

What is good

Open weights available
Accepts text, image, and video
262,144-token context window
Tool, vision, and reasoning support
$0.0675 input per 1M tokens

What to know first

Output costs $0.225 per 1M tokens
Produces text only
Maximum output is 235,929 tokens

Verdict

Gemma 4 26B A4B combines open weights with multimodal inputs, tools, vision, and reasoning. Its pricing and large context window make the model relevant for teams planning broad input handling.

Details

Lab: Googleopenrouter.ai · 3 Oct 2026
Context: 262Kopenrouter.ai · 3 Oct 2026
Input price: $0.068 / 1Mopenrouter.ai · 3 Oct 2026
Output price: $0.225 / 1Mopenrouter.ai · 3 Oct 2026
Max output: 235,929 tokensopenrouter.ai · 3 Oct 2026
Inputs: image, text, videoopenrouter.ai · 3 Oct 2026
Open weights: Yesopenrouter.ai · 3 Oct 2026

More newest models

See the list

Ling 3.1 Flash ctx262KinFreeoutFree inclusionAI Apodex 1.1 Mini (free) ctx262KinFreeoutFree Apodex Pareto 26.10 Preview ctx1,049Kin$0.8 / 1Mout$3.2 / 1M unbiased GPT-6.1 Sol ctx1,050Kin$2 / 1Mout$10 / 1M OpenAI GPT-6.1 Sol Pro ctx1,050Kin$2 / 1Mout$10 / 1M OpenAI Claude Sonnet 5.5 ctx1,000Kin$2 / 1Mout$10 / 1M Anthropic

Listed on Inferse

Newest Models in 2026466 listed
Longest-Context Models in 2026466 listed
Cheapest Language Models in 2026437 listed
Models with Tool Calling in 2026395 listed
Reasoning Models in 2026332 listed
Vision Language Models in 2026295 listed
Open-Weight Models in 2026178 listed
Google Models: Pricing per 1M Tokens and Context (2026)43 listed

Sources

openrouter.ai/google/gemma-4-26b-a4b-it· checked 3 Oct 2026