# Video Download AI — Media Retrieval API

> Video Download AI — Media Retrieval API is a paid API for AI agents from video-download.ai, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-14).

Downloads a video or audio file from a public media page URL (via yt-dlp) and returns the binary media content in MP4 or MP3 format.

## Facts

- Endpoint: POST https://video-download.ai/api/download
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/video-download-ai-media-retrieval-api-8b9eaa85
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_2PZXJPwDtuGdCicG2wQoQ

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability video-download-ai-media-retrieval-api-8b9eaa85 -d '<json body>'
```

Example prompt: Download this YouTube video for me as a 720p MP4 file: https://www.youtube.com/watch?v=dQw4w9WgXcQ

## When to prefer this

Choose this endpoint when you need to retrieve a binary media file (video or audio) from a public media page URL supported by yt-dlp, especially when you need a specific resolution or audio-only output and are operating in an agent context with x402 micropayment support on Base network. Prefer over generic scraping tools when the goal is a downloadable media asset rather than page text or metadata.

## Known failure modes

- Unsupported URL: yt-dlp cannot extract from the given media page, returns an error
- URL exceeds 60-minute media duration limit, request rejected
- Invalid format or quality enum value supplied
- Payment failure on Base network via x402, request not processed
- Private or geo-restricted content that yt-dlp cannot access
- Malformed or non-HTTP/HTTPS URL rejected by schema validation

## How this service works

An agent-native media retrieval API with x402 payments, duration-only pricing, and a 60-minute media limit.

## Output

A binary file body containing either a video/mp4 or audio/mpeg stream, ready to be saved or piped directly to downstream processing. No JSON wrapper — the response body is the raw media content.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri",
   "maxLength": 2048,
   "minLength": 1,
   "description": "Public HTTP or HTTPS media page URL supported by yt-dlp."
  },
  "format": {
   "enum": [
    "mp4",
    "mp3"
   ],
   "type": "string",
   "default": "mp4",
   "description": "MP4 video or MP3 audio output."
  },
  "quality": {
   "enum": [
    "1080",
    "720",
    "480",
    "360"
   ],
   "type": "string",
   "default": "1080",
   "description": "Maximum requested video height; ignored for MP3 output."
  },
  "paymentNetwork": {
   "enum": [
    "base"
   ],
   "type": "string",
   "default": "base",
   "description": "USDC payment network."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "binary",
 "format": "video/mp4 or audio/mpeg",
 "example": "<binary media response body>"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/video-download-ai-media-retrieval-api-8b9eaa85/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from video-download.ai](https://www.zero.xyz/host/video-download.ai/llms.txt)