---
title: "Follow an object through a video (a mask video)"
method: POST
path: "/v1/ai/track-object"
tags: ["Object tracking"]
---

# Follow an object through a video (a mask video)

`POST /v1/ai/track-object`

## Request

- Base URL: `https://apihub.co.il`
- URL: `https://apihub.co.il/v1/ai/track-object`
- Auth: HTTP bearer

Finds what you name ("the bottle", "the red car"; several with commas) in a video (up to 60 s) and follows it frame by frame (SAM 3). `output: "mask"` (the default) returns a black-and-white video of the same length — white where the object is — for an effect, a colour pop or a blur that follows the object; `overlay` returns the object highlighted over the video, to check what was found.

Per-frame box coordinates are not returned by the model (`boxes: null`). Asynchronous: poll `GET /v1/executions/{id}`. Price: per frame of the input video — see `POST /v1/ai/track-object/estimate`.

**Billing:** Per frame of the input video (charged per second of it). A failed request is not charged. · **Rate limit:** 10/min · **Asynchronous**

## Headers

- `Idempotency-Key` string
- `X-Tag` string
- `x-wait-ms` integer

## Request body

- object
  - `output` 'mask' | 'overlay': mask (the default) = a black-and-white video of the same length, white where the object is — for effects that follow it · overlay = the object highlighted over the video (a preview)
  - `prompt` string, required: What to follow, in a few words: "the bottle", "the red car" — several things with commas: "person, dog"
  - `video_url` string, uri, required: The video (up to 60 s)
  - `duration_seconds` number: The video's length if you know it (only for the estimate)
  - `detection_threshold` number: How sure the model must be to follow something (lower finds more, less precisely; try 0.3 when nothing is found)

## Response `200`

Completed (or 202 while processing)

- object
  - `id` string: Execution id — stable across internal retries; use it with GET /v1/executions/{id}
  - `status` 'pending' | 'processing' | 'completed' | 'partial' | 'failed' | 'cancelled' | 'timeout'
  - `operation` string
  - `tag` string, nullable: Your X-Tag, if sent
  - `created_at` string, date-time
  - `completed_at` string, date-time, nullable
  - `output` object: Operation result (see each operation). While a Studio render is processing: `stage` (queued · transcribing · downloading · preparing · cleaning_voice · mixing_audio · rendering · finishing), `phase` (the engine's: download · prepare · voice · audio · encode · qa · upload, or null), `progress` (a percent, 0–100) and `progress_fraction` (0–1), `eta_seconds` (seconds left, never below 0) and `estimate_seconds`
  - `error` string, nullable
  - `usage` object
    - `credits_charged` number, nullable
    - `credits_reserved` number
    - `estimated_credits` number
    - `cost_source` 'provider_reported' | 'calculated' | 'estimated' | 'null', nullable
    - `provider_usage` object, nullable: Normalised consumption, e.g. { VIDEO_SECOND: 22.4 }
  - `balance` object
    - `available` number
    - `reserved` number

## Other responses

- `202`: Processing — poll GET /v1/executions/{id}
- `400`: Invalid input
- `402`: Insufficient credits / project budget
- `404`: Resource not found (or not yours)
- `429`: Rate limited
- `503`: Service temporarily paused

---

[API](https://skmtc.dev/apihub/apis/apihub-one-api-for-chat-image-video-ai.md) · [All operations](https://skmtc.dev/apihub/apis/apihub-one-api-for-chat-image-video-ai/llms.txt) · [OpenAPI document](https://skmtc.dev/apihub/apis/apihub-one-api-for-chat-image-video-ai/revisions/a8caa42835ce?raw)