Gemma 4 26B A4B IT
Gemma 4 26B A4B IT is Google DeepMind's instruction-tuned mixture-of-experts model with 25.2B total and 3.8B active parameters, making it an excellent choice for fast inference compared with larger dense models.
text + image → text · made by Google
$0.1→$0.3per Mtok in / out
Cloudflare
Sold by 5 ways
| Seller | Lane | Rate |
|---|---|---|
| Cloudflare 0 ways | $0.1per Mtok in$0.3per Mtok out | |
| Cloudflare aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.3per Mtok outdevelopers.cloudflare.com · read 2026-08-25 |
| Cloudflare aggregatornot on the seller's list today | sandbox | $0.1per Mtok in$0.3per Mtok outdevelopers.cloudflare.com · read 2026-08-25 |
| SiliconFlow 0 ways | $0.12per Mtok in$0.4per Mtok out | |
| SiliconFlow aggregatornot on the seller's list today | standard | $0.12per Mtok in$0.4per Mtok outmodels.dev · read 2026-08-27 |
| ElectronHub 0 ways | $0.13per Mtok in$0.4per Mtok out | |
| ElectronHub aggregatornot on the seller's list today | standard | $0.13per Mtok in$0.4per Mtok outapi.electronhub.ai · read 2026-08-27 |
| Hugging Face Inference Providers 0 ways | $0.13per Mtok in$0.4per Mtok out | |
| Hugging Face Inference Providers aggregatornot on the seller's list today | standard | $0.13per Mtok in$0.4per Mtok outmodels.dev · read 2026-08-27 |
About
Gemma 4 26B A4B IT — a text model from Google.
It takes text and images and returns text, with a context window of 256,000 tokens. It was published in April 2026. Its sellers say it can reason step by step and call a tool. The catalogue files it under chat.
Every current figure
- Maker
- Register
- model
- Takes
- text + image
- Returns
- text
- Context
- 256,000 tokens
- Longest answer
- 16,384 tokens
- Published
- April 2026
- Parameters
- 26 billion · read from its own name, the total of a mixture
- Licence
- not read
Known as 1 name
@cf/google/gemma-4-26b-a4b-it