tripo3d/tripo-h3.1/text-to-3d
Tripo H3.1 is Tripo3D's text-to-3D AI model. Turn written descriptions into textured 3D objects with realistic geometry and materials.
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/runtripo3d/tripo-h3.1/text-to-3dInput Schema
1 parameters · 1 required · 0 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Required | Text description of the 3D object to generate. Maximum 1024 characters. · Max length: 1024 |
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": "tripo3d/tripo-h3.1/text-to-3d",
"prompt": "A small house with a red roof and white walls"
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Tripo H3.1 Text to 3D
Tripo H3.1 Text-to-3D converts a written object description into a downloadable 3D asset, giving artists and product teams a rapid starting point for geometry that does not yet exist. The route is suited to props, characters, merchandise concepts, and environment pieces where a natural-language brief should become an inspectable spatial form.
H3.1 focuses on the complete asset rather than a flat preview: the generated result can include geometry and materials suitable for downstream inspection and refinement. A concise prompt should identify silhouette, proportions, construction, surface treatment, and intended style so the model can resolve both the object's form and its visual character.
Highlights
Text-to-3D asset creation. Turns a natural-language object brief into a downloadable three-dimensional result.
Geometry and material synthesis. Produces spatial form together with surface appearance rather than only a rendered concept image.
Fast concept blocking. Provides an initial asset for visualization, prototyping, and art-direction review before manual refinement.
Wide subject coverage. Supports prompts for props, products, stylized characters, architectural pieces, and environment assets.
Pricing
| Texture tier | Base price |
|---|---|
| None | $0.100 |
| Standard | $0.200 |
| HD | $0.300 |
| Optional enhancement | Added price |
|---|---|
| Detailed geometry | +$0.200 |
| Quad mesh | +$0.050 |
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 small house with a red roof and white walls"
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | tripo3d/tripo-h3.1/text-to-3d |
| Inputs | prompt |
| Required inputs | prompt |
| Output fields | content_type, url |
| Execution | Async (submit, then poll for result) |
Related Models
tripo3d/tripo-h3.1/image-to-3d— Compare a nearby route in the same local model family.tripo3d/tripo-h3.1/multiview-to-3d— Compare a nearby route in the same local model family.tripo3d/tripo-p1/image-to-3d— Compare a nearby route in the same local model family.