# ScalingTensor

> ScalingTensor is a pay-as-you-go API for 23 AI models for video generation, music generation, sound effects and video dubbing. One API key and one prepaid wallet cover every model in the catalog.

## API facts

- API base: https://restapi.scalingtensor.com
- Authentication: apiKey request header (not Authorization: Bearer). Create keys in the console after signing in with Google.
- Media: POST /api/media/generate with {"model": "<model ID>", "params": {...}}; poll GET /api/media/result?jobId=... until completed or failed.
- Chat: POST /api/chat/completion with model and messages.
- Responses use code, data and msg; code 0 means success. The API is not OpenAI wire-compatible, so OpenAI SDK clients need an adapter.
- Public catalog: GET /models/list (no key needed).
- Billing: prepaid wallet, top-ups from $10, no subscription. Each model is billed per call, per second, per token or at provider cost.

## Start here

- [Agent setup instructions](https://scalingtensor.com/SKILL.md): how a coding agent should obtain a key and call a model
- [API reference (Markdown)](https://scalingtensor.com/docs/api.md)
- [Everything in one file](https://scalingtensor.com/llms-full.txt): API reference plus every model's parameters
- [Pricing](https://scalingtensor.com/pricing)
- [Model catalog](https://scalingtensor.com/models)

## Providers

- [Kling API](https://scalingtensor.com/providers/kling): 14 models. Kling is the video generation model family from Kuaishou.
- [Sonilo API](https://scalingtensor.com/providers/sonilo): 5 models. Sonilo builds audio generation models for music, sound effects and dubbing.
- [BytePlus API](https://scalingtensor.com/providers/byteplus): 4 models. BytePlus is ByteDance's enterprise technology business; it serves the Dreamina Seedance video models.

## Tasks

- [Image to Video API](https://scalingtensor.com/tasks/image-to-video): 10 models. Animate a still image into a video clip.
- [Text to Video API](https://scalingtensor.com/tasks/text-to-video): 8 models. Generate a video clip from a written prompt.
- [Video to Video API](https://scalingtensor.com/tasks/video-to-video): 8 models. Generate a new video from an existing clip.
- [4K Video API](https://scalingtensor.com/tasks/4k): 5 models. Video generation models that output 4K resolution.
- [Motion Control API](https://scalingtensor.com/tasks/motion-control): 2 models. Transfer the movement in a reference video onto the subject of an image.
- [Music Generation API](https://scalingtensor.com/tasks/music-generation): 2 models. Generate original music from a prompt or from a video.
- [Sound Effects API](https://scalingtensor.com/tasks/sound-effects): 2 models. Generate sound effects from a prompt or from a video.
- [Reference to Video API](https://scalingtensor.com/tasks/reference-to-video): 1 model. Generate video that follows reference images for characters, objects and style.
- [Text to Music API](https://scalingtensor.com/tasks/text-to-music): 1 model. Compose a music track from a text description.
- [Text to Sound Effects API](https://scalingtensor.com/tasks/text-to-sfx): 1 model. Generate a sound effect from a text description.
- [Video Dubbing API](https://scalingtensor.com/tasks/video-dubbing): 1 model. Dub the speech in a video into other languages.
- [Video Editing API](https://scalingtensor.com/tasks/video-editing): 1 model. Edit an existing video with a natural-language instruction.
- [Video to Music API](https://scalingtensor.com/tasks/video-to-music): 1 model. Score a video with music generated to fit it.
- [Video to Sound Effects API](https://scalingtensor.com/tasks/video-to-sfx): 1 model. Add sound effects that match what happens in a video.

## Models

Each model links to its web page; append .md under /docs for the Markdown version.

- [Dreamina Seedance 2.0](https://scalingtensor.com/models/dreamina-seedance-2-0-260128) ([Markdown](https://scalingtensor.com/docs/models/dreamina-seedance-2-0-260128.md)): `dreamina-seedance-2-0-260128`; Provider cost USD / 1M completion tokens; varies by resolution and video input
- [Dreamina Seedance 2.0 Fast](https://scalingtensor.com/models/dreamina-seedance-2-0-fast-260128) ([Markdown](https://scalingtensor.com/docs/models/dreamina-seedance-2-0-fast-260128.md)): `dreamina-seedance-2-0-fast-260128`; Provider cost USD / 1M completion tokens; varies by resolution and video input
- [Dreamina Seedance 2.0 Mini](https://scalingtensor.com/models/dreamina-seedance-2-0-mini-260615) ([Markdown](https://scalingtensor.com/docs/models/dreamina-seedance-2-0-mini-260615.md)): `dreamina-seedance-2-0-mini-260615`; Provider cost USD / 1M completion tokens; varies by resolution and video input
- [Dreamina Seedance 2.5](https://scalingtensor.com/models/dreamina-seedance-2-5-260628) ([Markdown](https://scalingtensor.com/docs/models/dreamina-seedance-2-5-260628.md)): `dreamina-seedance-2-5-260628`; Provider cost USD / 1M completion tokens; varies by resolution and video input
- [Kling 3.0 Omni Pro Video Edit](https://scalingtensor.com/models/kwaivgi/kling-video/3.0/omni/pro/video-to-video/edit) ([Markdown](https://scalingtensor.com/docs/models/kwaivgi/kling-video/3.0/omni/pro/video-to-video/edit.md)): `kwaivgi/kling-video/3.0/omni/pro/video-to-video/edit`; ≈ $0.84 per clip, reference price
- [Kling 3.0 Omni Pro Video Reference](https://scalingtensor.com/models/kwaivgi/kling-video/3.0/omni/pro/video-to-video/reference) ([Markdown](https://scalingtensor.com/docs/models/kwaivgi/kling-video/3.0/omni/pro/video-to-video/reference.md)): `kwaivgi/kling-video/3.0/omni/pro/video-to-video/reference`; ≈ $0.84 per clip, reference price
- [Kling 3.0 Turbo Pro Image to Video](https://scalingtensor.com/models/kwaivgi/kling-video/3.0/turbo/pro/image-to-video) ([Markdown](https://scalingtensor.com/docs/models/kwaivgi/kling-video/3.0/turbo/pro/image-to-video.md)): `kwaivgi/kling-video/3.0/turbo/pro/image-to-video`; ≈ $0.70 per clip, reference price
- [Kling 3.0 Turbo Pro Text to Video](https://scalingtensor.com/models/kwaivgi/kling-video/3.0/turbo/pro/text-to-video) ([Markdown](https://scalingtensor.com/docs/models/kwaivgi/kling-video/3.0/turbo/pro/text-to-video.md)): `kwaivgi/kling-video/3.0/turbo/pro/text-to-video`; ≈ $0.70 per clip, reference price
- [Kling 3.0 Turbo Standard Image to Video](https://scalingtensor.com/models/kwaivgi/kling-video/3.0/turbo/standard/image-to-video) ([Markdown](https://scalingtensor.com/docs/models/kwaivgi/kling-video/3.0/turbo/standard/image-to-video.md)): `kwaivgi/kling-video/3.0/turbo/standard/image-to-video`; ≈ $0.56 per clip, reference price
- [Kling 3.0 Turbo Standard Text to Video](https://scalingtensor.com/models/kwaivgi/kling-video/3.0/turbo/standard/text-to-video) ([Markdown](https://scalingtensor.com/docs/models/kwaivgi/kling-video/3.0/turbo/standard/text-to-video.md)): `kwaivgi/kling-video/3.0/turbo/standard/text-to-video`; ≈ $0.56 per clip, reference price
- [Kling Video O3 4k Image to Video](https://scalingtensor.com/models/kwaivgi/kling-video/o3/4k/image-to-video) ([Markdown](https://scalingtensor.com/docs/models/kwaivgi/kling-video/o3/4k/image-to-video.md)): `kwaivgi/kling-video/o3/4k/image-to-video`; ≈ $2.10 per clip, reference price
- [Kling Video O3 4k Reference to Video](https://scalingtensor.com/models/kwaivgi/kling-video/o3/4k/reference-to-video) ([Markdown](https://scalingtensor.com/docs/models/kwaivgi/kling-video/o3/4k/reference-to-video.md)): `kwaivgi/kling-video/o3/4k/reference-to-video`; ≈ $2.10 per clip, reference price
- [Kling Video O3 4k Text to Video](https://scalingtensor.com/models/kwaivgi/kling-video/o3/4k/text-to-video) ([Markdown](https://scalingtensor.com/docs/models/kwaivgi/kling-video/o3/4k/text-to-video.md)): `kwaivgi/kling-video/o3/4k/text-to-video`; ≈ $2.10 per clip, reference price
- [Kling Video V3 4k Image to Video](https://scalingtensor.com/models/kwaivgi/kling-video/v3/4k/image-to-video) ([Markdown](https://scalingtensor.com/docs/models/kwaivgi/kling-video/v3/4k/image-to-video.md)): `kwaivgi/kling-video/v3/4k/image-to-video`; ≈ $2.10 per clip, reference price
- [Kling Video V3 4k Text to Video](https://scalingtensor.com/models/kwaivgi/kling-video/v3/4k/text-to-video) ([Markdown](https://scalingtensor.com/docs/models/kwaivgi/kling-video/v3/4k/text-to-video.md)): `kwaivgi/kling-video/v3/4k/text-to-video`; ≈ $2.10 per clip, reference price
- [Kling Video V3 Pro Image to Video](https://scalingtensor.com/models/kwaivgi/kling-video/v3/pro/image-to-video) ([Markdown](https://scalingtensor.com/docs/models/kwaivgi/kling-video/v3/pro/image-to-video.md)): `kwaivgi/kling-video/v3/pro/image-to-video`; ≈ $0.84 per clip, reference price
- [Kling Video V3 Pro Motion Control](https://scalingtensor.com/models/kwaivgi/kling-video/v3/pro/motion-control) ([Markdown](https://scalingtensor.com/docs/models/kwaivgi/kling-video/v3/pro/motion-control.md)): `kwaivgi/kling-video/v3/pro/motion-control`; ≈ $0.84 per clip, reference price
- [Kling Video V3 Standard](https://scalingtensor.com/models/kwaivgi/kling-video/v3/standard/motion-control) ([Markdown](https://scalingtensor.com/docs/models/kwaivgi/kling-video/v3/standard/motion-control.md)): `kwaivgi/kling-video/v3/standard/motion-control`; ≈ $0.63 per clip, reference price
- [Sonilo Video Dubbing](https://scalingtensor.com/models/sonilo/dubbing) ([Markdown](https://scalingtensor.com/docs/models/sonilo/dubbing.md)): `sonilo/dubbing`; $0.0985 per second of source video, multiplied by the number of languages
- [Sonilo Text to Music](https://scalingtensor.com/models/sonilo/text-to-music) ([Markdown](https://scalingtensor.com/docs/models/sonilo/text-to-music.md)): `sonilo/text-to-music`; $0.00225 per second of output, multiplied by the number of variants_num
- [Sonilo Text to Sound Effects](https://scalingtensor.com/models/sonilo/text-to-sfx) ([Markdown](https://scalingtensor.com/docs/models/sonilo/text-to-sfx.md)): `sonilo/text-to-sfx`; $0.0018 per second of output
- [Sonilo Video to Music](https://scalingtensor.com/models/sonilo/video-to-music) ([Markdown](https://scalingtensor.com/docs/models/sonilo/video-to-music.md)): `sonilo/video-to-music`; $0.009 per second of source video
- [Sonilo Video to Sound Effects](https://scalingtensor.com/models/sonilo/video-to-sfx) ([Markdown](https://scalingtensor.com/docs/models/sonilo/video-to-sfx.md)): `sonilo/video-to-sfx`; $0.009 per second of source video

## Guides

- [Text-to-Video, Image-to-Video or Video-to-Video? Choosing a Video Generation API](https://scalingtensor.com/blog/choosing-a-video-generation-api): Which kind of video model fits which job: text-to-video, image-to-video, reference images, motion control, editing and 4K, with the current models and prices for each.
- [How to Generate Video with the Kling API: Submit, Poll and Download](https://scalingtensor.com/blog/kling-video-api-guide): A complete walkthrough of Kling video generation through one API: choosing a Kling model, writing the request, polling the job, downloading the clip, and what it costs.
- [Video to Music API: Add a Generated Soundtrack to Any Video](https://scalingtensor.com/blog/video-to-music-api): How to score a video with music generated to fit it: the request, keeping dialogue audible, changing style across scenes, and what a minute of video costs.
- [AI Video Dubbing API: Translate the Voice in a Video into Other Languages](https://scalingtensor.com/blog/ai-video-dubbing-api): How to dub a video into several languages with one API call: the request, language codes, background ducking and how the price is calculated.
- [Async Media Generation APIs: Polling, Timeouts and Retries Done Right](https://scalingtensor.com/blog/async-media-api-polling): Video and audio generation jobs take seconds to minutes. How to submit them, poll without hammering the API, survive restarts, and avoid paying twice for the same job.