deepinfra-gemma-4-26b-a4b-it

by Google

A Mixture-of-Experts model that activates only 4B parameters per inference,delivering high-performance reasoning with a fraction of the memory cost - idealfor cost-efficient, high-throughput server deployments.

API Pricing

Input	$0.09 / 1M tokens
Output	$0.38 / 1M tokens
Cache read	$0.01 / 1M tokens

Specifications

Context window

262,100 tokens

Use deepinfra-gemma-4-26b-a4b-it via the AIHubMix unified API — one interface for every major LLM.