Models

Gemini 4 Argon

Google · October 2026

Google's model for hard coding, math and science problems, and for agents that work through many steps. It reads images and PDFs, with a 1M-token context.

  • Modalities

  • Context window

    1,048,576 tokens, ≈ 786,000 words · about 3,150 pages

  • Max output

    65,536 tokens, ≈ 49,000 words in a single answer

  • Knowledge cutoff

    March 2026

Reasoning effort

Default: Medium

  • Low

  • Medium

  • High

Providers

Files you can attach

  • ImagesJPG, PNG, WEBP, HEIC, HEIF
  • DocumentsPDF
  • Text and codeTXT, MD, CSV, TSV, RPT, LOG, PY, TS, TSX, JS, JSX, CS, GO, JAVA, KT, SWIFT, CPP, C, H, PHP, RB, SQL, SH, PS1, HTML, CSS, SCSS, JSON, YAML, YML, XML, INI

Tools

  • Web searchSupported
  • File searchSupported
  • Image generationNot supported
  • Code interpreterSupported

Features

  • StreamingSupported
  • Function callingSupported
  • Structured outputsSupported
  • Fine-tuningNot supported

Ready to try it?

Log in

Bring your own API key · Your chats stay in your browser