Models

GPT-5.6 Luna

OpenAI · July 2026

Built for conversation. The fastest and cheapest GPT-5.6, for everyday questions.

Superseded by GPT-6 Luna →

  • Modalities

  • Context window

    1,050,000 tokens, ≈ 788,000 words · about 3,150 pages

  • Max output

    128,000 tokens, ≈ 96,000 words in a single answer

  • Knowledge cutoff

    February 2026

Reasoning effort

Default: Medium

  • None

  • Low

  • Medium

  • High

  • X-High

  • Max

Providers

Files you can attach

  • ImagesJPG, PNG, GIF, WEBP
  • DocumentsPDF, DOCX, XLSX, PPTX
  • 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 generationSupported
  • Code interpreterSupported
  • Hosted shellSupported
  • Apply patchSupported
  • SkillsSupported
  • Computer useSupported
  • MCPSupported
  • Tool searchSupported

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