Work with Gemini 4 Argon
in AdaL
Google's flagship reasoning model for complex software engineering and multi-step agent work. Use gemini-4-argon in AdaL with 1M context and low, medium, or high thinking.
Get StartedRun /model and pick Gemini 4 Argon · $2/M input · $10/M output (intro pricing through Nov 30, 2026)
Why use Gemini 4 Argon in AdaL
Key capabilities and pricing
Flagship reasoning
Google's model for the hardest coding and agent tasks.
Thinking levels
Low, medium (default), or high thinking depth.
Multimodal
Reads images, video, audio and PDFs alongside text.
1M context
A 1M-token window shared by input and output.
$2/M input · $10/M output
Introductory pricing through Nov 30, 2026; $4 / $20 after.
How to pick Gemini 4 Argon
Available in AdaL CLI and Desktop through the model selector
Open AdaL CLI or AdaL Desktop
Use the coding environment where AdaL already understands your repo, tools, and task context.
Run /model
Open the model selector and choose your model from the list.
Start your task
Ask AdaL to inspect, plan, edit, test, and review with your chosen model powering the agent loop.
What to know
Key details about Gemini 4 Argon
"Gemini 4 Argon is Google’s flagship reasoning model."
"A 1M-token window shared by input and output."
Context
"$2 / $10 per 1M tokens through Nov 30, 2026, then $4 / $20."
Pricing
"Available now in AdaL CLI and Desktop."
Availability
Ready to try Gemini 4 Argon in AdaL?
Open AdaL CLI or Desktop, run /model, and choose Gemini 4 Argon.
Get Started with AdaL