seedinteger
Random seed for reproducibility
SAM 3 3D Objects
meta/sam-3/3d-objectsSam 3 3d Objects by Meta - convert 2D images into 3D models with AI. Generate textured 3D assets from single photos for games, AR/VR, e-commerce, and digital content creation.
Try the model
Playground
Input
Text prompt for auto-segmentation when no masks provided (e.g., 'chair', 'lamp')
PNG, JPEG, WebP, or GIF · 20 MiB maximum
URL of the image to reconstruct in 3D
This field is required.
Additional Settings More
Customize your input with more control.
Point prompts for auto-segmentation when no masks provided
0.11
Detection confidence threshold (0.1-1.0). Lower = more detections but less precise. If not set, uses the model's default. Range: 0.1 to 1.
Box prompts for auto-segmentation when no masks provided. Multiple boxes supported - each produces a separate object mask for 3D reconstruction.
Optional URL to external pointmap/depth data (NPY or NPZ format) for improved 3D reconstruction depth estimation
If True, exports GLB with baked texture and UVs instead of vertex colors.
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.
Random seed for reproducibility
ResultIdle
Your output will appear here
Complete the inputs, then click Run.
SAM 3 3D Objects
SAM 3D Objects reconstructs a segmented object from a single image as a 3D model.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | car | What to reconstruct. |
image | image URL, required | — | Image containing the object. JPEG, PNG, or WebP URL. |
point_prompts | object[] | [] | Point prompts for auto-segmentation when no masks provided |
detection_threshold | number 0.1–1 | — | Detection confidence threshold (0.1-1.0). |
box_prompts | object[] | [] | Box prompts for auto-segmentation when no masks provided. |
pointmap_url | string | — | Optional URL to external pointmap/depth data (NPY or NPZ format) for improved 3D reconstruction depth estimation |
export_textured_glb | boolean | false | Export a textured GLB. |
mask_urls | image URL[] | — | Optional list of mask URLs (one per object). |
seed | integer | random | Fix it to compare prompt changes. |
Billing
$0.024 per object.
| Request | Price |
|---|---|
| One object | $0.024 |
Failed runs are not charged.
Also on SandBase
Related: meta/sam-3/image.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "meta/sam-3/3d-objects",
"image": "https://static.sandbase.ai/examples/meta/sam-3/3d-objects/input_image_0.jpeg",
"prompt": "car",
"box_prompts": [],
"point_prompts": [],
"export_textured_glb": false
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"2. Authentication
Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
3. Queue
Submit a request
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Fetch request status and result
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"4. Files
Hosted files
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Uploading images
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
5. Schema
Input
imagestringrequired
URL of the image to reconstruct in 3D
promptstringrequired
Text prompt for auto-segmentation when no masks provided (e.g., 'chair', 'lamp')
Default: "car"
mask_urlsarray
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_promptsarray
Box prompts for auto-segmentation when no masks provided. Multiple boxes supported - each produces a separate object mask for 3D reconstruction.
Default: []
pointmap_urlstring
Optional URL to external pointmap/depth data (NPY or NPZ format) for improved 3D reconstruction depth estimation
point_promptsarray
Point prompts for auto-segmentation when no masks provided
Default: []
detection_thresholdnumber
Detection confidence threshold (0.1-1.0). Lower = more detections but less precise. If not set, uses the model's default.
Minimum: 0.1
Maximum: 1
export_textured_glbboolean
If True, exports GLB with baked texture and UVs instead of vertex colors.
Default: false
{
"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
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
No example output has been published yet. Use Playground → Result → JSON after a completed run to inspect your response.