Gemma 4 26B A4B
google/
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
$0.07425 in · $0.2475 out per 1M tokens262k contextApr 3, 2026
A typical message: about 500 tokens you send and 500 it writes.
Also:free
Spec sheet
Published facts from the catalog, billed prices and what we measured here. Anything not measured says so.
Price, billed here
- Input, per 1M tokens
- $0.07425provider $0.0675
- Output, per 1M tokens
- $0.2475provider $0.225
- Cached input, per 1M
- $0.04125provider $0.0375
- Margin
- +10%
Context and formats
- Context window
- 262,144 tokens
- Longest answer
- 235,929 tokens
- Reads
- text, images, and video
- Makes
- text
- First listed
- 2026-04-03
Measured here, last 7 days
- First token, median
- not measured
- Answered without error
- not measured
Tools and JSON
- Tool calling
- declaredthe provider's claim, not yet measured here
- JSON output
- declaredthe provider's claim, not yet measured here
Price and latency history as JSON: GET /.
About
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...
In Google's words.
Try it here
Measured here
Call it
Use one OpenAI compatible endpoint, this model's id and an am_live_ key from the dashboard. You can also try it in chat first with no key.
curl https://useantimatter.com/v1/chat/completions \
-H "Authorization: Bearer $ANTIMATTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "google/gemma-4-26b-a4b-it", "messages": [{"role": "user", "content": "Hello"}]}'Everything else is in the docs.
Embed this
A badge showing this model's live price per million tokens, as billed here, for a README or a site. It links back to this page.
<a href="https://useantimatter.com/planet/google/gemma-4-26b-a4b-it"><img src="https://useantimatter.com/api/badge/price?id=google%2Fgemma-4-26b-a4b-it" alt="Gemma 4 26B A4B price on Antimatter" height="28"></a>More from Google
Similar models from other labs
Closest in price and memory, from other labs.
Go back to the map, or take this model into a chat.