AI Video Generation API
Text-to-video, image-to-video and video-to-video from Google, ByteDance, MiniMax, Runway, Alibaba and others, through one endpoint. Priced per second of video, paid per call.
29 models from 10 providers: Alibaba, Vidu, RunwayML, PixVerse, MiniMax, Google, ByteDance, GlianaAI, Lightricks, Bria.
Models
| Model | Provider | Price |
|---|---|---|
| wan-2.7-i2v | Alibaba | $0.1800 Default per second |
| hh1-i2v | Alibaba | $0.4060 Default per second |
| q3-pro | Vidu | $0.2175 Default per second |
| q3-turbo | Vidu | $0.1015 Default per second |
| gen-4.5 | RunwayML | $0.2610 Default per second |
| aleph-2 | RunwayML | $0.4872 Default per second |
| v6 | PixVerse | $0.1305 Default per second |
| v5.6 | PixVerse | $0.1740 Default per second |
| hailuo-2.3-fast | MiniMax | $0.0798 Default per second |
| hailuo-2.3 | MiniMax | $0.1184 Default per second |
| veo-3.1-fast | $0.1740 Default per second | |
| veo-3.1 | $0.5800 Default per second | |
| seedance-2.0-fast | ByteDance | $0.1160 Default per second |
| seedance-2.0 | ByteDance | $0.7975 Default per second |
| seedance-2.5 | ByteDance | $0.3352 Default per second |
| hh1-t2v | Alibaba | $0.4060 Default per second |
| hh1.1-t2v | Alibaba | $0.2610 Default per second |
| hh1.1-i2v | Alibaba | $0.2610 Default per second |
| hh1.1-r2v | Alibaba | $0.2610 Default per second |
| seedance-2.0-mini | ByteDance | $0.1595 Default per second |
| brainrot-video | GlianaAI | $1.0500 Per video |
| ltx-2-5-fast | Lightricks | $0.5365 Default per second |
| wan-3.0 | Alibaba | $0.2900 Default per second |
| wan-3.0-prime | Alibaba | $0.4060 Default per second |
| gemini-omni-flash | $4.4092 Per video (by resolution) | |
| gemini-omni-1.1-flash | $4.4092 Per video (by resolution) | |
| h3 | MiniMax | $0.1885 Default per second |
| h3-max | MiniMax | $0.1160 Default per second |
| v-rmbg-3.0 | Bria | $0.0326 Default per second |
Call it
The first response is 402 with the exact price and every way to pay. Pay,
repeat the request with the proof, and you get the result.
curl -X POST https://api.glianalabs.com/v1/video/generations \
-H 'content-type: application/json' \
-d '{"model":"seedance-2.0","prompt":"a paper boat drifting down a rainy street","duration":5}'How it works
POST /v1/video/generations takes a model, a prompt and, for image-to-video, a source image. Duration, resolution and aspect ratio are each model’s own options. The finished video is stored and returned as a URL.
Limits worth knowing
Set duration and resolution yourself. When they are missing, the call is priced at the model’s longest duration and highest resolution, because that is the most the provider can bill us. Video takes time to render, and URLs expire after 7 days.
Questions
How is AI video priced?
Per second of output, at each model’s rate, with resolution where the model charges by it. The quote is for the duration and resolution in your request.
Why was I quoted more than expected?
The request left duration or resolution unset, so it was priced at the maximum. Send both to pay for what you actually want.
Can I animate an image?
Yes. Use an image-to-video model and pass the image URL; local files go to /v1/media first.
Is there a free tier?
No. Every call is paid individually, with no plan or minimum. A request that fails validation is refused before it runs, so it is never charged.
Do I need an account or an API key?
No. The first response is HTTP 402 with the exact price; pay it with USDC from your own wallet and repeat the request. To prepay instead, top up a balance in rupiah and send a gk_ key.