Meta modelsimage generation api

meta/sam-3/3d-align

Name: SAM 3 3D Align
Author: Meta

Sam 3 3d Align by Meta - advanced AI model for 3d-to-3d. Delivers high-quality results with fast inference, suitable for both creative and production workflows.

Input

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL of the original image used for MoGe depth estimation

This field is required.

Focal Length(number)

Focal length from SAM-3D Body metadata. If not provided, estimated from MoGe.

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL of the human mask image. If not provided, uses full image.

Body Mesh Url(string)

URL of the SAM-3D Body mesh file (.ply or .glb) to align

Object Mesh Url(string)

Optional URL of SAM-3D Object mesh (.glb) to create combined scene

Idle

Example output — click Run to generate your own

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-align

Input Schema

5 parameters · 1 required · 4 optional

Parameter	Type	Required	Description
`image`	string	Required	URL of the original image used for MoGe depth estimation
`focal_length`	number	Optional	Focal length from SAM-3D Body metadata. If not provided, estimated from MoGe.
`body_mask_url`	string	Optional	URL of the human mask image. If not provided, uses full image.
`body_mesh_url`	string	Optional	URL of the SAM-3D Body mesh file (.ply or .glb) to align
`object_mesh_url`	string	Optional	Optional URL of SAM-3D Object mesh (.glb) to create combined scene

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

# 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": "meta/sam-3/3d-align",
  "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"

← Back to SAM 3 3D Align

API README

Sam 3 3D Align

Sam 3 3D Align is built for promptable segmentation and reconstruction, with this exact route focused on 3D reconstruction alignment. Sam 3 3d Align by Meta - advanced AI model for 3d-to-3d. Delivers high-quality results with fast inference, suitable for both creative and production workflows. It is designed for production workflows that need a clearly scoped media operation instead of a generic assistant response, preserving the supplied direction while returning an artifact ready for review, iteration, or downstream assembly.

The request surface keeps creative direction and delivery choices explicit through image_url, sync_mode, focal_length, body_mask_url, body_mesh_url, object_mesh_url. Teams can lock source material, describe the intended result, choose supported output controls, and rerun the same request structure across variations. This makes experiments easier to compare and larger pipelines easier to operate without hiding important decisions inside an opaque preset.

Highlights

3D Reconstruction Alignment. The meta/sam-3/3d-align route is dedicated to 3D reconstruction alignment, keeping inputs and outputs matched to this operation.
Precise Spatial Selection. Within meta/sam-3/3d-align, documented prompt and media controls direct precise spatial selection while keeping the brief close to the result.
Structured Masks Or Geometry. The meta/sam-3/3d-align result provides structured masks or geometry in a machine-consumable form for review and downstream production.
Route-specific control. For meta/sam-3/3d-align, documented controls include image_url, sync_mode, focal_length, body_mask_url, body_mesh_url, object_mesh_url, defining the supported variation space for this exact route.

Pricing

Configuration	Price
Per request	`$0.020000`

When to Use

Scenario	Why it fits
Choose this route	When the deliverable is specifically 3D reconstruction alignment, not a neighboring generation or editing task.
Production iteration	When creative teams need repeatable precise spatial selection with an explicit request payload.
Automated pipelines	When structured masks or geometry must flow into review, storage, compositing, or publishing.
Controlled variations	When a stable brief should be rerun while changing only documented inputs.
Prototype to scale	When the same `meta/sam-3/3d-align` contract should serve a single experiment and a larger batch later.

Prompt Guide

Lead with the subject or source, then state the transformation, important spatial or temporal details, style, and finish. Supply only documented fields, keep media URLs reachable, and vary one control at a time when comparing outputs.

{
  "image": "https://example.com/reference.jpg"
}

Technical Specs

Property	Value
Model ID	`meta/sam-3/3d-align`
Required inputs	`image`
`image_url`	string
`sync_mode`	boolean; default: false
`focal_length`	number
`body_mask_url`	string
`body_mesh_url`	string
`object_mesh_url`	string
`safety_tolerance`	string; default: 6
`image`	string; required

Related Models

meta/sam-3/3d-body
meta/sam-3/3d-objects
meta/sam-3/image
meta/sam-3/image-rle