The AIVEED.IO Video API
Generate video, images and audio from your own code. The same models and the same credits as the web app — reachable over plain HTTP.
New accounts get up to 200 free credits. Until you buy a credit pack, an account can make one video (any model and options that fit within those credits), counted across the web app and the API, so you can try the API end to end once.
What you can generate
Video generation
Text-to-video and image-to-video across the same model catalogue the web app uses — including first/last-frame control, reference images and video extension.
Image generation
Generate or edit images and feed the result straight into a video call as a first frame, without downloading and re-uploading it.
Audio generation
Voiceover and music, so a full narrated clip can be assembled from a single integration.
One call to your first video
curl -X POST "https://api.aiveed.io/v1/generate/video" \
-H "X-API-Key: $AIVEED_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "veo3-fast", "prompt": "A drone shot over snowy mountains at sunrise"}'
# → { "id": "job_...", "status": "submitted", "credits_charged": ..., ... }Then poll GET /v1/jobs/{id}, stream it over SSE, or register a webhook. Full walkthrough in the quickstart.
Built for production
Asynchronous by default
Every generation returns a job id immediately. Poll it, stream progress over SSE, or register a webhook and let us call you.
Signed webhooks
Delivery is HMAC-signed with a timestamp so you can verify the callback really came from us and reject replays.
Failures are refunded
If a provider fails a job, the credits it charged are returned automatically. You are not billed for output you never received.
Idempotency built in
Send an Idempotency-Key and a retried request returns the original job instead of generating — and charging — a second one.
Pricing
There is no separate API plan and no subscription. API calls draw on the same credit balance as the web app, so credits you buy work in either place. The cost depends on the model and the options you pick: resolution and length for video, length for voiceover and lip sync. Failed jobs are refunded, and the pricing endpoint lists every price.
Friendly to coding agents
The API ships a generated OpenAPI specification and a machine-readable llms.txt, so an AI assistant can read the whole surface and write a working integration without guesswork.