API reference · Bria
bria/video/background-removal/3.0
Integrate this model through SandBase's unified API, with production-ready schemas and examples.
Production endpoint
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
POST
https://api.sandbase.ai/v1/runModel ID
bria/video/background-removal/3.001
Input Schema
5 parameters · 0 required · 5 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
video | string | Optional | Input video to remove background from. |
auto_zoom | boolean | Optional | If true, crop the output to the smallest rectangle the subject stays inside for the whole video. · Default: false |
preserve_audio | boolean | Optional | If true, audio will be preserved in the output video. · Default: true |
background_color | string | Optional | Background color. Options: Transparent, Black, White, Gray, Red, Green, Blue, Yellow, Cyan, Magenta, Orange. · Options: Transparent, Black, White, Gray, Red, Green, Blue, Yellow, Cyan, Magenta, Orange · Default: "Black" TransparentBlackWhiteGrayRedGreenBlueYellowCyanMagentaOrange |
output_container_and_codec | string | Optional | Output container and codec. Options: mp4_h265, mp4_h264, webm_vp9, mov_h265, mov_proresks, mkv_h265, mkv_h264, mkv_vp9, gif. · Options: mp4_h265, mp4_h264, webm_vp9, mov_h265, mov_proresks, mkv_h265, mkv_h264, mkv_vp9, gif · Default: "webm_vp9" mp4_h265mp4_h264webm_vp9mov_h265mov_proresksmkv_h265mkv_h264mkv_vp9gif |
02
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
03
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "bria/video/background-removal/3.0",
"video": "https://bria-datasets.s3.us-east-1.amazonaws.com/rmbg_tests/videos/video.mp4",
"auto_zoom": false,
"preserve_audio": true,
"background_color": "Black",
"output_container_and_codec": "webm_vp9",
"prompt": "a beautiful sunset over mountains"
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"
