Gemini 4 Argon is now available. Try it out.

Gemini 4 Argon

Gemini 4 Argon (gemini-4-argon) is our flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, autonomous multi-step agents, and long decode up to 1M tokens.

Try in Google AI Studio

Documentation

Visit the Latest model page for full coverage of features, API changes, and migration guidance.

gemini-4-argon

Property	Description
Model code	`gemini-4-argon`
Supported data types	Inputs Text, Image, Video, Audio, and PDF Output Text
Token limits^[*]	Context window (unified input and output token limit) 1,048,576 Max output 65,536 (default synchronous) / up to 1,048,576 (with long decode)
Capabilities	Agentic video understanding Supported (defaults to `static`) Audio generation Not supported Caching Supported (Implicit only) Note: Explicit caching is not supported. Code execution Supported Computer use Supported (Preview) File search Supported Function calling Supported Grounding with Google Maps Supported Image generation Not supported Live API Not supported Search grounding Supported Structured outputs Supported Thinking Supported (low, medium, high) URL context Supported
Consumption options	Batch API Supported Flex inference Supported Priority inference Supported
Versions	Read the model version patterns for more details. Stable: `gemini-4-argon`
Latest update	October 2026
Model card	Model card