Question 1

What is Gemma 4 26B A4B?

Accepted Answer

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...

Question 2

How much does Gemma 4 26B A4B cost?

Accepted Answer

Gemma 4 26B A4B is priced at $0.06 per million input tokens and $0.33 per million output tokens.

Question 3

What is Gemma 4 26B A4B's context window?

Accepted Answer

Gemma 4 26B A4B supports a context window of 262,144 tokens, allowing it to process approximately 350 words in a single request.

Question 4

Is Gemma 4 26B A4B available via API?

Accepted Answer

Yes, Gemma 4 26B A4B is available via API. Developers can integrate it directly into their applications through Google's API platform.

Gemma 4 26B A4B

Model Overview

Vetted Benchmarks

How does this model compare?