Video Blade API
Protocols for your AI agent, storage for everything it creates, and image, video and music generation paid with tokens.
How it works
- Sign up at https://app.video-blade.com and top up your token balance.
- Pick a mode: your own local agent (Claude Code or compatible) connected through a protocol link, or the hosted Video Blade agent in the app (beta).
- Connect the agent: copy the protocol link from Settings into an empty project folder and ask the agent to follow it. The agent creates the project through the API and pulls the other protocols.
- Generate: the agent orders image, video and music generations with the model you chose for the project. Tokens are charged per actual consumption.
Authentication
Every request carries your API key from Settings, in either header:
X-API-Key: vb_…
Authorization: Bearer vb_…
curl -s https://app.video-blade.com/api/v1/me -H "X-API-Key: $VB_API_KEY"
Task lifecycle
Generations are asynchronous. Creating a task returns immediately with a task id; the result is delivered by polling or by a callback URL you pass in the request. A successful creation only means the task was accepted, not finished. Tokens are held when the task is created and settled when it completes; a failed task releases the hold.
The unified generation endpoint (
POST /api/v1/generations) ships with stage 1. Model pages already document every parameter you will pass in input.Explore
- Image models — 61 models
- Video models — 90 models
- Music models — 23 models
- Speech & audio — 6 models
- Chat models (hosted agent) — 35 models
- Pricing & tokens