Skip to main content
Video → depth map video. Turn a video into a depth map: a video that shows how near or far each part of the scene is. In the default grayscale, near is white and far is black, and the result is steady from frame to frame, at the input’s frame size and frame rate. The endpoint is POST /v1/depth-maps/{model}. Use it when a video model should follow the layout and motion of a clip you already have, without its colours. The depth video works as a reference video; see Use the result as a reference video. The colour maps (turbo, inferno, magma, viridis) are for looking at the depth yourself.

​
Model

1 model. Each name opens its API reference with every parameter.

​
How a request works

  1. Send POST /v1/depth-maps/video-depth-anything with the video and any options. The response returns a job id right away (it starts with dpt_), with the price in credits.
  2. Poll GET /v1/depth-maps/{id} until status is succeeded. The response then holds the depth video’s URL in video_url.
Media inputs covers passing the video, and Async jobs covers job statuses and errors. A job is pending, processing, succeeded, failed or canceled; the last three are final.

​
Sizes and pricing

size picks the model size, which sets the price. A depth map is priced per second of the input video, rounded up to whole seconds, with a 5-second minimum. Only the size and the length of the input set the price. The output resolution, colormap, keep_audio and side_by_side don’t change it. A 12.4-second clip at large bills as 13 seconds, 13 × 40 = 520 credits. A 3-second clip at small bills as 5 seconds, 5 × 20 = 100 credits. POST /v1/cost quotes a request before you send it. Send the size and the clip’s length in seconds:
Leave out seconds to get only the rates: credits_per_second, size_pricing and min_seconds. GET /v1/models?type=video-depth lists the model with credits_per_unit: 20 (the small rate) and size_pricing, the rate for every size. You pay only for jobs that succeed; see Pricing & credits.

​
Example

Create the job. This turns a clip into a large grayscale depth map:
The response comes back at once. seconds is the length you’re billed for and credits is the price:
Poll the job until status is succeeded:
If a job fails, status is failed and error_message says why. Failed jobs aren’t charged.

​
Parameters

Every parameter is also on the API reference page. POST /v1/uploads takes files up to 50 MB. For a larger video, up to 100 MB, pass a public URL instead. The input video is checked against BudgetPixel’s content policy before the job starts, like every other input. A blocked request returns 400 and isn’t charged; see content moderation blocks.

​
The result

  • Format. An H.264 MP4. The poll response reports video_codec: "h264".
  • Frame size and rate. The input’s frame size, up to 1080p (or the resolution you chose), and the input’s frame rate, up to 30 fps.
  • Look. In grayscale, near is white and far is black.
  • Audio. The input’s audio is copied only when keep_audio is true.
  • Download it. video_url is a short-lived signed URL; call the poll endpoint again for a fresh one. The file itself is deleted 24 hours after generation, so download it if you need to keep it.

​
Use the result as a reference video

A depth map keeps a clip’s layout and motion and drops its colour, which makes it a structure and motion reference for video models. Take the finished job’s video_url, pass it where a video model accepts a reference video (for example reference_videos on SeeDance 2.5), and describe the scene you want in the prompt.
  • Keep the default grayscale colormap for this. It’s the one video models take as a depth reference.
  • Leave side_by_side off for a reference clip: it adds the input video next to the depth map.
  • Use the URL right away or download the file, since it’s deleted after 24 hours.
The Video generation API lists the video models, and Video generation modes shows which inputs each one takes.