RentGPU RentGPU
Find a GPU →
by Google DeepMind

Google: Gemini 4 Argon.

multimodal closed 1M ctx
Cheapest input
$2.0/M
on OpenRouter
Cheapest output
$10.0/M
on OpenRouter
Hosted equiv.
~$3.6/hr
@ 100 tok/s on OpenRouter

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...

Hosted API only

No self-host path — closed weights.

Google: Gemini 4 Argon'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
OpenRouter api aggregator $2.0 $10.0 Launch ↗
FAQ

Frequently asked.

How do I run Google: Gemini 4 Argon?
Google: Gemini 4 Argon 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: Gemini 4 Argon?
Google: Gemini 4 Argon is available via OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Google: Gemini 4 Argon?
API pricing starts at $2.0/M input tokens and $10.0/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Google: Gemini 4 Argon open-source or proprietary?
Google: Gemini 4 Argon is a proprietary model from Google DeepMind. Access is API-only — there are no public weights to download.