Models

DeepSeek V4 Flash

DeepSeek · July 2026

Fast and cheap for conversation, hard problems and multi-step work. Not marketed for code — use V4 Pro for that.

Superseded by DeepSeek V4.1 Flash →

  • Modalities

  • Context window

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

  • Max output

    393,216 tokens, ≈ 295,000 words in a single answer

Reasoning effort

Default: High

  • Low

  • High

  • Max

Providers

Files you can attach

  • ImagesNot supported
  • 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

Tools

  • Web searchSupported

Ready to try it?

Log in

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