Google

Google: Gemma 4 26B A4B

google/gemma-4-26b-a4b-it-20260403Hugging Face ↗

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...

toolsstructuredreasoningimage in
Data source

Google: Gemma 4 26B A4B usage over time

OpenRouter share of tokens, by day.

View
Tidelines.ai

Google: Gemma 4 26B A4B holds 0.42% today, down from 0.58% at the start of the visible window.

Data: OpenRouter as of 2026-07-14

Rank history

Tidelines.ai
Data: OpenRouter as of 2026-07-14

Adoption curve vs the pantheon

Google: Gemma 4 26B A4B 's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?

Tidelines.ai
Data: OpenRouter as of 2026-07-14

Citable stat

As of 2026-07-14, Google: Gemma 4 26B A4B holds 0.4% of OpenRouter token share, down 0.20pp over 30 days. Source: Tidelines (OpenRouter).

Where to run it

Providers & pricing

Tidelines.ai

Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.

ProviderInput $/MOutput $/MContextUptime
Cloudflare$0.10$0.30256k98.33%
DekaLLM$0.06$0.33262k91.44%
DeepInfra$0.07$0.34262k99.86%
NextBit$0.12$0.35262k99.68%
SiliconFlow$0.12$0.40262k92.10%
Novita$0.13$0.40262k99.21%
Parasail$0.13$0.40262k98.04%
Venice$0.13$0.40256k97.73%
Wafer$0.13$0.40262k97.05%
Google$0.15$0.60262k89.60%