hyper3d/rodin
Rodin is hyper3d's image-to-3D AI model. Transform photographs into production-ready 3D meshes with accurate geometry and texture mapping.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runhyper3d/rodinInput Schema
12 parameters · 1 required · 11 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Required | A textual prompt to guide model generation. Required for Text-to-3D mode. Optional for Image-to-3D mode. · Max length: 1024 · Default: "" |
seed | integer | Optional | Seed value for randomization, ranging from 0 to 65535. Optional. · Min: 0 · Max: 65535 |
tier | string | Optional | Tier of generation. For Rodin Sketch, set to Sketch. For Rodin Regular, set to Regular. · Options: Regular, Sketch · Default: "Regular" RegularSketch |
TAPose | boolean | Optional | When generating the human-like model, this parameter control the generation result to T/A Pose. · Default: false |
addons | string | Optional | Generation add-on features. Default is []. Possible values are HighPack. The HighPack option will provide 4K resolution textures instead of the default 1K, as well as models with high-poly. It will cost triple the billable units. |
quality | string | Optional | Generation quality. Possible values: high, medium, low, extra-low. Default is medium. · Options: high, medium, low, extra-low · Default: "medium" highmediumlowextra-low |
material | string | Optional | Material type. Possible values: PBR, Shaded. Default is PBR. · Options: PBR, Shaded · Default: "PBR" PBRShaded |
use_hyper | boolean | Optional | Whether to export the model using hyper mode. Default is false. · Default: false |
bbox_condition | integer[] | Optional | An array that specifies the dimensions and scaling factor of the bounding box. Typically, this array contains 3 elements, Length(X-axis), Width(Y-axis) and Height(Z-axis). |
condition_mode | string | Optional | For fuse mode, One or more images are required.It will generate a model by extracting and fusing features of objects from multiple images.For concat mode, need to upload multiple multi-view images of the same object and generate the model. (You can upload multi-view images in any order, regardless of the order of view.) · Options: fuse, concat · Default: "concat" fuseconcat |
input_image_urls | string[] | Optional | URL of images to use while generating the 3D model. Required for Image-to-3D mode. Optional for Text-to-3D mode. |
geometry_file_format | string | Optional | Format of the geometry file. Possible values: glb, usdz, fbx, obj, stl. Default is glb. · Options: glb, usdz, fbx, obj, stl · Default: "glb" glbusdzfbxobjstl |
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, ortimeout - Retrieve — Read
outputsfrom 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": "hyper3d/rodin",
"tier": "Regular",
"TAPose": false,
"prompt": "A futuristic robot with sleek metallic design.",
"quality": "medium",
"material": "Shaded",
"use_hyper": false,
"condition_mode": "concat",
"input_image_urls": [
"https://static.sandbase.ai/examples/hyper3d/rodin/input_input_image_urls_0.png"
],
"geometry_file_format": "glb"
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Hyper3D Rodin
hyper3d/rodin creates a textured three-dimensional asset from a concise object brief and available visual references. Rodin reconstructs a production-oriented 3D asset with geometry and appearance from visual or written guidance, reducing the time needed to block a spatial concept manually. This combination makes the model a practical choice when the creative outcome depends on those qualities rather than on a generic media conversion.
For production work with hyper3d/rodin, the workflow is useful for product concepts, characters, props, collectibles, and environment pieces that need an editable spatial starting point. The result is most reliable when the source material and creative brief clearly describe the intended subject, progression, visual or sonic character, and the qualities that must remain unchanged.
Highlights
3D asset synthesis builds complete geometry rather than only a rendered turntable.
Texture generation gives the reconstructed object a coherent material appearance.
Multi-view reasoning resolves shape and details consistently around the asset.
Downloadable output supports inspection, iteration, and downstream 3D workflows.
Pricing
| Billing unit | Price |
|---|---|
| Per request | $0.4 |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| The model's named workflow matches the source material and intended output | A different input modality or model route is required |
| A managed asynchronous result is suitable for the production pipeline | A synchronous, interactive editor is essential |
| The documented controls cover the required duration, framing, or format | The project needs controls outside this endpoint's schema |
| Creative iteration benefits from a repeatable request structure | Exact deterministic pixels, frames, geometry, or samples are mandatory |
| A finished downloadable media asset is the desired deliverable | Editable source layers or a native project file are required |
Prompt Guide
For generation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.
{
"prompt": "A futuristic robot with sleek metallic design."
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | hyper3d/rodin |
| Inputs | TAPose, addons, bbox_condition, condition_mode, geometry_file_format, input_image_urls, material, prompt, quality, seed, tier, use_hyper |
| Required inputs | prompt |
| Output fields | content_type, url |
| Execution | Async (submit, then poll for result) |
| Quality | high / medium / low / extra-low |

