API reference · Meta

meta/sam-3/video-rle

Integrate this model through SandBase's unified API, with production-ready schemas and examples.

IMAGEAsyncOpen model

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDmeta/sam-3/video-rle

Input Schema

9 parameters · 1 required · 8 optional

Parameter	Type	Required	Description
`prompt`	string	Required	Text prompt for segmentation. Use commas to track multiple objects (e.g., 'person, cloth'). · Default: ""
`mask`	string	Optional	The URL of the mask to be applied initially.
`video`	string	Optional	The URL of the video to be segmented.
`apply_mask`	boolean	Optional	Apply the mask on the video. · Default: false
`box_prompts`	object[]	Optional	List of box prompts with optional frame_index. · Default: []
`frame_index`	integer	Optional	Frame index used for initial interaction when mask_url is provided. · Default: 0
`point_prompts`	object[]	Optional	List of point prompts with frame indices. · Default: []
`boundingbox_zip`	boolean	Optional	Return per-frame bounding box overlays as a zip archive. · Default: false
`detection_threshold`	number	Optional	Detection confidence threshold (0.0-1.0). Lower = more detections but less precise. Defaults: 0.5 for existing, 0.7 for new objects. Try 0.2-0.3 if text prompts fail. · Min: 0.01 · Max: 1 · Default: 0.5

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, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

const apiKey = process.env.SANDBASE_API_KEY;
const response = await fetch("https://api.sandbase.ai/v1/run", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "meta/sam-3/video-rle",
    "video": "https://static.sandbase.ai/examples/meta/sam-3/video-rle/input_video_0.mp4",
    "prompt": "person",
    "apply_mask": false,
    "box_prompts": [],
    "frame_index": 0,
    "point_prompts": [],
    "boundingbox_zip": false,
    "detection_threshold": 0.5
  }),
});

if (!response.ok) throw new Error(await response.text());
let result = await response.json();
for (let attempt = 0; attempt < 120 && !["completed", "failed", "timeout"].includes(result.status); attempt++) {
  await new Promise((resolve) => setTimeout(resolve, 2_000));
  const poll = await fetch(`https://api.sandbase.ai/v1/run/${result.id}`, {
    headers: { Authorization: `Bearer ${apiKey}` },
  });
  if (!poll.ok) throw new Error(await poll.text());
  result = await poll.json();
}
if (result.status !== "completed") throw new Error(`Generation ended: ${result.status}`);
console.log(result);

← Back to Sam 3