SAM 3D Objects
SAM 3D Objects is a foundation 3D model from Meta that reconstructs full 3D shape geometry, realistic texture, and scene layout of objects from a single RGB image. It produces high-fidelity 3D meshes robustly even in cluttered, occluded real-world scenes, and significantly outperforms prior single-image 3D methods. SAM 3D Objects is part of the broader SAM 3D family, enabling 2D-to-3D reconstruction workflows for visualization, AR/VR, robotics, and digital content creation.
API Options
Platform-level options for task execution and delivery.
-
taskType
string required value: 3dInference -
Identifier for the type of task being performed
-
taskUUID
string required UUID v4 -
UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.
-
outputType
string default: URL -
3D output type.
Allowed values 1 value
-
outputFormat
string default: GLB -
Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.
- `GLB`: Binary glTF format for 3D models, including geometry, textures, and PBR materials.
Allowed values 1 value
-
webhookURL
string URI -
Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.
Learn more 1 resource
- Webhooks PLATFORM
- Webhooks
-
deliveryMethod
string default: async -
Determines how the API delivers task results.
Allowed values 2 values
- Returns complete results directly in the API response.
- Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.
Learn more 1 resource
- Task Polling PLATFORM
-
uploadEndpoint
string URI -
Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.
Common use cases:
- Cloud storage: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- CDN integration: Upload to content delivery networks for immediate distribution.
// S3 presigned URL for secure upload https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600 // Google Cloud Storage presigned URL https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789 // Custom storage endpoint https://storage.example.com/uploads/generated-image.jpgThe content data will be sent as the request body to the specified URL when generation is complete.
-
ttl
integer min: 60 -
Time-to-live (TTL) in seconds for generated content. Only applies when
outputTypeisURL.
-
includeCost
boolean default: false -
Include task cost in the response.
-
numberResults
integer min: 1 max: 4 default: 1 -
Number of results to generate. Each result uses a different seed, producing variations of the same parameters.
Inputs
Input resources for the task (images, audio, etc). These must be nested inside the inputs object.
inputs object. Generation Parameters
Core parameters for controlling the generated content.
-
model
string required value: meta:sam@3d -
Identifier of the model to use for generation.
Learn more 3 resources
-
positivePrompt
string -
Text prompt describing elements to include in the generated output.
Learn more 2 resources
-
seed
integer min: 0 max: 9223372036854776000 -
Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.
Learn more 1 resource
Cluttered Workshop Toy Robot
{
"taskType": "3dInference",
"taskUUID": "0bfd1f7c-213a-4cc4-b44d-ce9eace8e1c3",
"model": "meta:sam@3d",
"positivePrompt": "Reconstruct a high-fidelity 3D mesh of the toy robot from the provided RGB image, preserving dented tin surfaces, painted facial details, small screws, boxy limbs, and believable thickness where parts are partially hidden by surrounding tools.",
"seed": 90625,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/5dc78892-3d96-4a0a-a91f-36f5d4c09271.jpg",
"mask": "https://assets.runware.ai/assets/inputs/64fc9d20-f4f6-44a3-9473-4827f3797479.jpg"
}
}{
"taskType": "3dInference",
"taskUUID": "0bfd1f7c-213a-4cc4-b44d-ce9eace8e1c3",
"seed": 90625,
"cost": 0.0038,
"outputs": {
"files": [
{
"uuid": "4a01c929-ccd1-4d15-85c8-1df84d198a20",
"url": "https://im.runware.ai/image/os/a02d21/ws/4/ii/4a01c929-ccd1-4d15-85c8-1df84d198a20.glb"
}
]
}
}Velvet Astrolabe on Marble
{
"taskType": "3dInference",
"taskUUID": "d96c26c4-5483-4561-9e13-304732ca7db4",
"model": "meta:sam@3d",
"positivePrompt": "Reconstruct a highly detailed 3D model of an antique brass astrolabe with engraved markings, layered rotating rings, delicate pointers, worn patina, and realistic metallic texture, preserving the object shape from a single RGB image with strong geometric fidelity and accurate surface detail.",
"seed": 6580,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/338367ac-0dcd-424f-82e7-1f4a1f3f0ac0.jpg"
}
}{
"taskType": "3dInference",
"taskUUID": "d96c26c4-5483-4561-9e13-304732ca7db4",
"seed": 6580,
"cost": 0.0038,
"outputs": {
"files": [
{
"uuid": "5f8a2d02-c5cc-4fa0-97b3-7abdf8a15507",
"url": "https://im.runware.ai/image/os/a24d12/ws/4/ii/5f8a2d02-c5cc-4fa0-97b3-7abdf8a15507.glb"
}
]
}
}Weathered Violin Workshop Stilllife
{
"taskType": "3dInference",
"taskUUID": "d5bc8455-8e83-40c5-ac1a-b2933272ffea",
"model": "meta:sam@3d",
"positivePrompt": "Reconstruct a high-fidelity 3D mesh of the masked violin from a single RGB image, preserving the elegant arched body, f-holes, strings, bridge, tailpiece, scroll details, subtle asymmetry from age, glossy amber-brown varnish, edge wear, and believable thickness; infer realistic backside geometry and coherent texture continuation for use in AR and product-style inspection",
"seed": 52232,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/b5c5651e-a075-4ca1-a6b4-9e0c0a24e6c9.jpg",
"mask": "https://assets.runware.ai/assets/inputs/44728544-6b3a-46d2-b205-6c2fc8a635a3.jpg"
}
}{
"taskType": "3dInference",
"taskUUID": "d5bc8455-8e83-40c5-ac1a-b2933272ffea",
"seed": 52232,
"cost": 0.0038,
"outputs": {
"files": [
{
"uuid": "e9bd2e7d-cebf-4b03-b7fb-e919526bd890",
"url": "https://im.runware.ai/image/os/a19d05/ws/3/ii/e9bd2e7d-cebf-4b03-b7fb-e919526bd890.glb"
}
]
}
}Mossy Forest Lantern Relic
{
"taskType": "3dInference",
"taskUUID": "b9d83f75-cc55-40d6-9e74-32a49c412430",
"model": "meta:sam@3d",
"positivePrompt": "Reconstruct a complete high-fidelity 3D object from a single RGB photo of an antique brass lantern with engraved filigree, cracked glass panes, oxidized metal, moss around the base, and slight occlusion from fern leaves, preserving realistic geometry, thin handle details, surface wear, and natural texture variation.",
"seed": 24216,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/9285ba9f-3a71-4984-bc39-62864814028d.jpg"
}
}{
"taskType": "3dInference",
"taskUUID": "b9d83f75-cc55-40d6-9e74-32a49c412430",
"seed": 24216,
"cost": 0.0038,
"outputs": {
"files": [
{
"uuid": "5737c54e-3bfa-4a51-ad58-00efe6868f2d",
"url": "https://im.runware.ai/image/os/a17d13/ws/4/ii/5737c54e-3bfa-4a51-ad58-00efe6868f2d.glb"
}
]
}
}Ceramic Koi Incense Burner
{
"taskType": "3dInference",
"taskUUID": "ba766912-31ee-4dc2-94b7-a1963256b080",
"model": "meta:sam@3d",
"positivePrompt": "Reconstruct a high-fidelity 3D model of a ceramic koi-shaped incense burner with glossy crackle glaze, perforated body vents, curved fins, and detailed surface texture from a single product-style image.",
"seed": 11641,
"inputs": {
"image": "https://assets.runware.ai/assets/inputs/a2fb0c84-c87b-4d2a-a8c6-9a57bbfbea04.jpg",
"mask": "https://assets.runware.ai/assets/inputs/19663f0e-0ae1-4e0a-90d1-73e3e827c73f.jpg"
}
}{
"taskType": "3dInference",
"taskUUID": "ba766912-31ee-4dc2-94b7-a1963256b080",
"seed": 11641,
"cost": 0.0038,
"outputs": {
"files": [
{
"uuid": "35f03c2a-09f3-49e9-bd81-57e08331012c",
"url": "https://im.runware.ai/image/os/a05d22/ws/3/ii/35f03c2a-09f3-49e9-bd81-57e08331012c.glb"
}
]
}
}