Model catalog profile

Google: Gemma 4 26B A4B | pricing profile

Start with Google: Gemma 4 26B A4B input $0.12, output $0.40, context 262,144, and provider Google, then decide whether this pricing path is worth exploring further.

Provider

Google

32 models in catalog

Context

262,144

global model route

Input

$0.12

USD / 1M tokens

Output

$0.40

USD / 1M tokens

What this page answers

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...

Google · google/gemma-4-26b-a4b-it
text+image+video->text · global model route
262,144 context · $0.12 input

Before connecting

Do not stop at the model name. Before integration, verify base URL, protocol, visible models, parameters, and limits together.

supports frequency_penalty
supports include_reasoning
supports logit_bias
supports logprobs
supports max_tokens

Next action

After this page, the usual next step is to open the model profile, the provider profile, or run a key check to confirm the real callable range.

Check whether the model fits the use case
Then verify key permission and callable models

Continue

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