API reference · Meta

meta/sam-3/3d-objects

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-3/3d-objects

Input Schema

9 parameters · 2 required · 7 optional

Parameter	Type	Required	Description
`image`	string	Required	URL of the image to reconstruct in 3D
`prompt`	string	Required	Text prompt for auto-segmentation when no masks provided (e.g., 'chair', 'lamp') · Default: "car"
`seed`	integer	Optional	Random seed for reproducibility
`mask_urls`	string[]	Optional	Optional list of mask URLs (one per object). If not provided, use prompt/point_prompts/box_prompts to auto-segment, or entire image will be used.
`box_prompts`	object[]	Optional	Box prompts for auto-segmentation when no masks provided. Multiple boxes supported - each produces a separate object mask for 3D reconstruction. · Default: []
`pointmap_url`	string	Optional	Optional URL to external pointmap/depth data (NPY or NPZ format) for improved 3D reconstruction depth estimation
`point_prompts`	object[]	Optional	Point prompts for auto-segmentation when no masks provided · Default: []
`detection_threshold`	number	Optional	Detection confidence threshold (0.1-1.0). Lower = more detections but less precise. If not set, uses the model's default. · Min: 0.1 · Max: 1
`export_textured_glb`	boolean	Optional	If True, exports GLB with baked texture and UVs instead of vertex colors. · Default: false

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-3/3d-objects",
    "image": "https://static.sandbase.ai/examples/meta/sam-3/3d-objects/input_image_0.jpeg",
    "prompt": "car",
    "box_prompts": [],
    "point_prompts": [],
    "export_textured_glb": false
  }),
});

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