# Google: Gemma 4 26B A4B  (free)

Provider: google  
Category: llm  
Model ID: `google/gemma-4-26b-a4b-it:free`

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...

## Specs

- Context length: 262144 tokens
- Max output: 32768 tokens
- Modalities: image, text, video
- Released: 2026-04-03

## Pricing

- Input: $0.00 per million tokens
- Output: $0.00 per million tokens

## Providers

- **google** — ctx 262144, input $0.00/M, output $0.00/M

---
Last verified: 2026-04-23T23:46:29.618Z  
Canonical URL: https://switchy.build/models/gemma-4-26b-a4b-it-free