Models · Google
Gemma 4 26B A4B
Released 3 Apr 2026Sees imagesTool useReasoning
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...
Input$0.09₹7.92 · per 1M tokens
Output$0.30₹26 · per 1M tokens
Context262Ktokens it can read at once
Max output236Ktokens per reply
What members say
From members who used it for real work. Facts above come from OpenRouter.
No reviews yet. Used it? Tell others what it was good or bad at.
Members can review models they've used.
What would it cost?
- Gemma 4 26B A4B $2.25 · ₹198 a month · $0.000 · ₹0.02 each
Estimate from list prices per token, at ₹88/$. Caching, batch discounts and taxes aren't included. A token is about ¾ of a word.