RentGPU RentGPU
Find a GPU →
by Google DeepMind

Google: Gemma 4 26B A4B .

multimodal closed laptop+ 26B params 262K ctx
Cheapest input
$0.07/M
on DeepInfra
Cheapest output
$0.255/M
on OpenRouter
Hosted equiv.
~$0.09/hr
@ 100 tok/s on OpenRouter

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...

Hosted API only

No self-host path — closed weights.

Google: Gemma 4 26B A4B 's weights aren't published. Use it via the access providers below.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
DeepInfra hosted inference $0.07 $0.34 Launch ↗
OpenRouter api aggregator $0.0765 $0.255 Launch ↗
Sources

Official references.

Hugging Face ↗
FAQ

Frequently asked.

How do I run Google: Gemma 4 26B A4B ?
Google: Gemma 4 26B A4B is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access Google: Gemma 4 26B A4B ?
Google: Gemma 4 26B A4B is available via Together AI, DeepInfra, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Google: Gemma 4 26B A4B ?
API pricing starts at $0.06/M input tokens and $0.33/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Google: Gemma 4 26B A4B open-source or proprietary?
Google: Gemma 4 26B A4B is a proprietary model from Google DeepMind. Access is API-only — there are no public weights to download.