MoGe 2
MoGe 2 by Microsoft reconstructs visible scene geometry from one JPG, PNG or WebP image up to 2048 × 2048 pixels and 20 MB. Download a textured GLB mesh, a colored PLY point cloud, colorized depth and validity maps, and camera field of view and intrinsics. Choose one of four checkpoints; normal-capable checkpoints also return surface normals. Processing detail, masking, edge filtering and an optional known horizontal field of view are adjustable. Reconstruction does not recover unseen surfaces or guarantee absolute scale. $0.01 per started decimal megapixel, minimum one megapixel; all options included.
Added Nov 7, 2026
Details
- Price per model
- $0.01/model
- Model type
- image-to-3d
- Typical duration
- ~2 min
- Inputs
- Image
- Image required
Price table
Each row is the price for one completed 3D model generation.
| Variant | Price |
|---|---|
Default Default | $0.01/model |
Settings
Generation controls available for this model.
Output Format
GLB
Checkpoint
Default
vitl-normal
Options (4)
Large with normals, Large without normals, Base with normals, Small with normals
Colored PLY point cloud
Default
Yes
Edge threshold
Default
0.04
Lower values remove more edges across depth discontinuities.
Known horizontal field of view
Optional, in degrees. Leave blank to estimate the camera.
Mask uncertain regions
Default
Yes
Processing detail
Default
9
Higher levels refine detail and take longer. Price depends on input image dimensions.
Safety checker
Default
Yes
Textured GLB mesh
Default
Yes
API request
Submit the generation with POST /api/generate-video, then poll the returned run ID for completion.
{
"model": "microsoft/moge-2",
"imageDataUrl": "data:image/png;base64,...",
"resolution_level": 9,
"apply_mask": true,
"edge_threshold": 0.04,
"export_glb": true,
"export_ply": true,
"enable_safety_checker": true,
"checkpoint": "vitl-normal"
}Browse the 3D models API catalogExamples
Loading examples…