How the PopNow API works

What the API can make, the five ideas every other page builds on, and the order to read things in.

The PopNow API lets your own software use the image, video and audio models you know from popnow.ai. Same models, same prices, same credits — just called from code instead of clicked in a browser.

What you can make

Output	Examples
Images	Text to image, image editing with one or more references, upscaling, background removal, layer separation
Video	Text to video, image to video, first-and-last-frame video, reference video, extending and editing clips, lip sync, talking avatars
Audio	Music, sound effects, text to speech, a soundtrack for an existing video, speech to text

The full list, with each model's ID and price, is on Models. The API covers image, video and audio generation only; chat and text models are not part of it.

Five ideas you will meet everywhere

Each thing you can call has an ID in the form <maker>/<model>/<task>, for example alibaba/wan-3.0/image-to-video or google/nano-banana-2.1/edit. You put it in the model field of every request. Image editing always ends in /edit. Tools built by PopNow itself, such as background removal, use popnow as the maker.

Task

Generation takes from a few seconds to several minutes, so every request creates a task. You get a taskId at once and read the result when it is ready. A task moves through queued → running → one final state: succeeded, failed or expired. Details: Tasks.

Credits

The API spends the same credits as the website. One credit is $0.01 at the base rate. When a task is accepted, its highest possible price is held; when it finishes, you pay the real amount (never more than the hold) and the rest is released. A task that fails costs nothing. Details: Billing.

Idempotency key

A network timeout does not tell you whether the server received your request. Send an Idempotency-Key header with every task you create, and a retry with the same key returns the original task instead of making — and charging — a second one. Details: Idempotency.

Webhook

Instead of asking for a task again and again, give it a callBackUrl. When the task finishes, PopNow sends the full result to that URL, signed so you can check it came from us. Details: Webhooks.

What a request looks like

POST https://api.popnow.ai/api/v1/jobs/createTask
Authorization: Bearer sk-popnow-...
Idempotency-Key: 7d0c9a52-...

{ "model": "alibaba/wan-3.0/image-to-video",
  "input": { "image_url": "https://…/photo.jpg", "prompt": "The waves roll in slowly" },
  "callBackUrl": "https://your-app.example.com/hooks/popnow" }

Every response uses one envelope, { "code", "msg", "data", "request_id" }, where code: 200 means success.

Read in this order

Quickstart — your first result in five minutes.
Authentication — how to keep a key safe and restrict what it can do.
Models — pick a model and read its parameters.
Tasks and Webhooks — the full lifecycle.
Media — send your own images, video and audio.
Errors and Rate limits — before you go live.

Want to try a model before writing code? Every model has a Playground on its API page on popnow.ai, which runs on your account with no key needed.