Visual Sandbox — Create With The Top AI Models

Spotlight search

Find any model, tool or page and jump to it.

Visual Sandbox

Ask for any visual.The agent knowswhat looks good.

Start creating
  • Google
  • OpenAI
  • ByteDance
  • Tencent
  • ElevenLabs
  • Black Forest Labs
  • Runway
  • Luma
  • Kling
  • MiniMax Hailuo
  • Pika
  • Stability AI
  • Recraft
  • Quiver
  • Wan

Pay-per-use workspace for AI image, video, vector, 3D, and audio generation.

vsb CLI · plays nice with Claude Code

Make anything with Claude Code

Tell Claude Code what you want and it makes it. It comes with skills that know how to prompt each model.

curl -fsSL visualsandbox.com/install.sh | sh && vsb setup
See it in action
Claude Code
>make a neon jellyfish drifting through a dark ocean
Bash(vsb run image/nano-banana --prompt "neon jellyfish…")
Done in 6s
Bash(vsb run video/p-video --image out.png --prompt "slow drift…")
Done in 12s · saved to your canvas
$

Every model

How it works

  1. 01Pick

    Every model in one place

    Image, video, vector, 3D and audio from Google, OpenAI, ByteDance and more.

  2. 02Prompt

    A crab on warm sand, golden hour
    Describe it, get it

    Write what you want. Attach a reference. Adjust the settings if you need finer control.

  3. 03Pay

    Charged per run
    Pay per generation

    No subscription. Card on file, charged per run. You see the price before you make it.

Techniques