Video

Perceptron provides an OpenRouter-compatible video generation API. Video models accept text prompts (and optional reference images) and generate short video clips. You pay using credits purchased with USDT.

Video generation is asynchronous: you submit a job, poll its status, and download the finished video. Generation typically takes a few minutes.

Base URL

https://perceptron.cloud/api/v1

Authentication

Include your API key in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Generate an API key from the Keys page in the Perceptron app.

Available Models

curl https://perceptron.cloud/api/v1/videos/models

Video models (the video output modality) are listed separately from chat models. The response includes each model’s supported resolutions, aspect ratios, duration range, audio support, and per-second pricing per resolution tier.

Generating Videos

1. Submit a job

POST /api/v1/videos

curl -X POST https://perceptron.cloud/api/v1/videos \
  -H "Authorization: Bearer $PERCEPTRON_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax/hailuo-3",
    "prompt": "A golden retriever playing fetch on a sunny beach with waves crashing in the background",
    "duration": 5,
    "resolution": "2K",
    "aspect_ratio": "16:9"
  }'

Returns 202 Accepted with the job details:

{
  "id": "0e1b0c3f-...",
  "polling_url": "/api/v1/videos/0e1b0c3f-...",
  "status": "pending"
}

Field	Type	Required	Description
`model`	string	yes	Video model ID from `GET /api/v1/videos/models`
`prompt`	string	yes	Text description of the video to generate
`duration`	integer	yes	Clip duration in seconds (per-model min/max)
`resolution`	string	no	Output resolution tier (e.g. `2K`); defaults to the model’s first supported tier
`aspect_ratio`	string	no	Aspect ratio (e.g. `16:9`, `9:16`, `1:1`)
`size`	string	no	Exact pixel dimensions in `WIDTHxHEIGHT` format; interchangeable with `resolution` + `aspect_ratio`
`generate_audio`	boolean	no	Whether to generate audio alongside the video (models with audio support)
`seed`	integer	no	Seed for deterministic generation (not guaranteed by all models)
`frame_images`	array	no	First/last frame images (image-to-video), each with a `frame_type` of `first_frame` or `last_frame`
`input_references`	array	no	Reference images for style guidance (reference-to-video)

callback_url and provider are not supported; rejected with 400.

2. Poll for status

GET /api/v1/videos/{id}

curl https://perceptron.cloud/api/v1/videos/0e1b0c3f-... \
  -H "Authorization: Bearer $PERCEPTRON_API_KEY"

{
  "id": "0e1b0c3f-...",
  "polling_url": "/api/v1/videos/0e1b0c3f-...",
  "status": "completed",
  "unsigned_urls": ["/api/v1/videos/0e1b0c3f-.../content?index=0"],
  "usage": { "cost": 1.5 }
}

Status	Description
`pending`	The job is queued
`in_progress`	The video is being generated
`completed`	The video is ready to download
`failed`	Generation failed (see `error`); the reservation is fully refunded
`cancelled`	The job was cancelled upstream; fully refunded
`expired`	The job exceeded its upstream time limit; fully refunded

Poll at a reasonable interval (e.g. every 5–30 seconds).

3. Download the video

GET /api/v1/videos/{id}/content

curl https://perceptron.cloud/api/v1/videos/0e1b0c3f-.../content \
  -H "Authorization: Bearer $PERCEPTRON_API_KEY" \
  --output video.mp4

Raw video bytes with Content-Type: video/mp4. Finished videos are stored as artifacts in your account.

Listing and deleting jobs

GET /api/v1/videos — list your video generation jobs, newest first.
DELETE /api/v1/videos/{id} — delete a job and its stored video, stopping its storage billing.

See the full reference at API Reference.

Pricing

Video generation is billed per output second from your credits balance — see the live per-resolution rates at GET /api/v1/videos/models. The full quoted cost is reserved when you submit and refunded if the job fails. Stored videos accrue a small hourly artifact storage charge until deleted. See Billing for more details.

Studio

The Perceptron app includes Studio, a browser interface for generating and managing videos without writing any code: open the app and select Studio in the sidebar.