Google: Gemini 4 Argon

Gemini 4 Argon is Google's multimodal reasoning model for complex coding, scientific problem solving, and multi-step agents. It accepts text, images, audio, video, and PDF input and produces text. Input, thinking, and output share a 1,048,576-token context window; ordinary synchronous requests support up to 65,536 output tokens. Google's long-decode mode can extend output to the remaining context budget through background execution or continuation. It supports tools, structured output, streaming, and implicit caching. Thinking levels are low, medium (default), and high. Sampling controls temperature, top_p, and top_k are ignored. Knowledge cutoff: March 2026.

Context window

1048576

Category

-

Last updated

2026-11-06

Providers

-