Models

Kimi K3

Moonshot AI · July 2026

Moonshot AI's open model for coding, knowledge work and long agent tasks. It reads images, with a 1M-token context.

  • Modalities

  • Context window

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

  • Max output

    1,048,576 tokens, ≈ 786,000 words in a single answer

Reasoning effort

Default: Max

  • Low

  • High

  • Max

Providers

Files you can attach

  • ImagesJPG, PNG, GIF, WEBP, HEIC, HEIF
  • DocumentsNot supported
  • 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

Ready to try it?

Log in

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