Tripo
Tripo H3.1
tripo-h3.1/image-to-3d
Tripo's high-detail 3D generation model, supporting the generation of textured 3D assets from text prompts, a single image, or multiple views, with adjustable polygon count and texture quality and PBR material output, suitable for asset creation such as game props and product visualization
Try tripo-h3.1/image-to-3d
Input
Upload one photo of a single object on a clean background; JPG, PNG and WEBP only.
Output
Pricing
tripo-h3.1/image-to-3d per model
+ $0.290 finer geometry
Positioning Overview
For developers and design teams that need to quickly generate 3D assets from a single photo. Just provide one HTTPS object image with a clean background, and you get a 3D model with geometry and optional textures, making it suitable for quickly converting real-object photos into digital assets that can be viewed, rendered, or further edited.
Core Highlights
- Generate a 3D model from a single image: provide a link to an object photo with a clean background to start generation, suitable for quickly digitizing real objects or design drawings.
- Geometry and texture controlled separately: you can disable both texture and PBR to get only a geometry mesh, or set quality levels for geometry and texture separately depending on the intended use.
- Face-count limit configurable: you can specify a target face count between 1,000 and 1.5 million triangles (2 million for detailed geometry), making it easy to match different downstream pipelines with different precision requirements.
- Reproducible results: random seeds can be set for both geometry and texture, and together with fixed parameters this makes repeated generation and result comparison easier.
Capability Description
Image to 3D mesh: input an HTTPS link to a single object photo and output a 3D model; when both texture and PBR are disabled, only a pure geometry mesh is produced, which is suitable for defining the shape first and processing later.
Face count target control: the face limit (face_limit) can be set to a target face count between 1,000 and 1.5 million triangles (2 million for detailed geometry); if left empty, the model decides adaptively, making it easy to match precision requirements for rendering or lightweight scenarios.
Texture and PBR switches: texture is enabled by default, and PBR materials are generated by default; enabling PBR forces texture generation, and only when both texture and PBR are disabled is geometry alone retained, so choose according to downstream use.
Quality level switching: geometry quality and texture quality can each be set to standard or detailed (standard / detailed); the detailed level brings finer mesh details and higher-resolution textures respectively.
Orientation and texture alignment: selecting "align to input image" (align_image) for orientation automatically rotates the model to match the input image; texture alignment (texture_alignment) can be set to fit the original image or fit the geometry.
Applicable Scenarios
- Converting real-object photos into digital assets: e-commerce or design teams use handheld-object photos to generate 3D models and place them on product display pages or in 3D viewers for users to rotate and inspect.
- Rapid 3D-ization of concept designs: concept designers convert sketches or reference images into 3D meshes and use them as a starting point for proportions and volumes in modeling software for further refinement.
- 3D foundation for marketing materials: marketing teams generate textured models from product images and import them into rendering or animation workflows to create 3D product assets for promotional images.
- Pre-generating lightweight assets: developers set a lower face count and standard textures to batch-generate 3D display assets suitable for mobile or real-time scenarios.
Limitations and Selection Advice
The input accepts only an HTTPS image link to a single object with a clean background; images with cluttered backgrounds or multiple objects in the same frame may not produce ideal geometry. The face count target is limited to between 1,000 and 1.5 million triangles (2 million for detailed geometry), and specifying a low face count loses detail; when texture and PBR are disabled, the output is untextured geometry. Texture alignment and orientation settings affect the final appearance and need to be chosen according to the input image; the generated result is not guaranteed to match the photo point by point.
What's new
View changelog →- New model tripo-h3.1/multiview-to-3d is live: Tripo H3.1 Multiview to 3D
- New model tripo-h3.1/text-to-3d is live: Tripo H3.1 Text to 3D
- New model tripo-h3.1/image-to-3d is live: Tripo H3.1 Image to 3D
Frequently asked questions
View all FAQs →-
What is the face count upper limit? Can it reach 2 million?
Yes, the face_limit upper bound is 2 million triangles, but 2 million is only actually supported when geometry_quality is set to detailed; under standard, it is recommended to set it within 1.5 million. If face_limit is not passed, the model adaptively determines the face count.
-
How do I get just a geometry without textures first?
Set both texture and pbr to false. When pbr is true, textures are forcibly generated. If you need textures but not a PBR material, set texture to true and pbr to false.
-
Should high-density geometry have its own separate parameter?
Setting geometry_quality to detailed adds finer mesh detail and is also the prerequisite for the polygon count to reach 2 million; if you need more refined textures, set texture_quality to detailed. Both default to standard, so enable them only as required by the close-up needs of the target asset.
-
How can I reproduce generation results so it's easy to compare different parameters?
Geometry and textures each have their own fixed seed: model_seed controls geometry, texture_seed controls textures, and text-to-3D additionally has image_seed to control the concept image. When comparing parameter settings, first fix the seeds and change only one parameter, so you can tell which item the difference comes from.
Create a generation task
https://api.hiapi.ai/v1/tasks Headers
AuthorizationstringRequiredAccount API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key
Content-TypestringOptionalThe request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.
Idempotency-KeystringOptionalIdempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.
On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.
Body
modelstringRequiredCurrent fixed value: tripo-h3.1/image-to-3d
routestringOptionalCurrent fixed value: default
inputobjectRequired
Business parameters for tripo-h3.1/image-to-3d and route default — see the parameter table below.
pbrbooleanOptionalDefault: trueControls whether PBR materials are generated; when set to true, texture maps are also generated. Default is true.
texturebooleanOptionalDefault: trueWhether to generate textures for the model. Default is true. Note that when pbr is true, textures are forcibly generated; only when both texture and pbr are set to false is a pure geometry mesh output.
image_urlstringRequiredpattern ^https://HTTPS address of a single object photo; the photo background must be clean. Used as the input image for image-to-3D.
face_limitintegerOptionalmin 1000max 2000000Target triangle count, as an integer, range 1000–1500000 (up to 2000000 when geometry_quality=detailed); when omitted, the model adaptively determines the face count. Files are usually large; for web display, around 50000 is recommended.
model_seedintegerOptionalRandom seed for geometry generation, as an integer, used to reproduce the same geometry result.
orientationstringOptionalDefault: "default"Controls model orientation; align_image automatically rotates to align based on the input image. Default is default.
defaultalign_imagetexture_seedintegerOptionalRandom seed for texture generation, as an integer, used to reproduce the same texture result.
texture_qualitystringOptionalDefault: "standard"Controls texture quality; detailed generates higher-resolution textures. Default is standard.
standarddetailedgeometry_qualitystringOptionalDefault: "standard"Controls geometry quality; detailed adds finer mesh details. Default is standard.
standarddetailedtexture_alignmentstringOptionalDefault: "original_image"Controls how the texture is aligned with the input image. Default is original_image.
original_imagegeometrycallbackobjectOptional
Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.
Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.
urlstringRequiredRequired when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.
whenstringOptionalDefault: "final"Only final is supported today — notified on both success and fail.
finalstoragestringOptionalDefault: "temp"Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.
temppersistentRequest examples
# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
-H "Authorization: Bearer $HIAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tripo-h3.1/image-to-3d",
"input": {
"pbr": true,
"texture": true,
"image_url": "…",
"orientation": "default",
"texture_quality": "standard",
"geometry_quality": "standard",
"texture_alignment": "original_image"
}
}' const res = await fetch("https://api.hiapi.ai/v1/tasks", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "tripo-h3.1/image-to-3d",
input: {
"pbr": true,
"texture": true,
"image_url": "…",
"orientation": "default",
"texture_quality": "standard",
"geometry_quality": "standard",
"texture_alignment": "original_image"
}
}),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } } import os, requests
res = requests.post(
"https://api.hiapi.ai/v1/tasks",
headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
json={
"model": "tripo-h3.1/image-to-3d",
"input": {
"pbr": True,
"texture": True,
"image_url": "…",
"orientation": "default",
"texture_quality": "standard",
"geometry_quality": "standard",
"texture_alignment": "original_image"
}
},
)
print(res.json()) # { code, message, data: { taskId } } 200 OK
{
"code": 200,
"message": "success",
"data": {
"taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
}
} 400 Bad Request
{
"code": 400,
"message": "invalid request",
"data": null,
"error_code": "INVALID_REQUEST"
} Get task detail
https://api.hiapi.ai/v1/tasks/:id Response fields
taskIdstringRequiredTask ID, always prefixed with tk-hiapi-.
modelstringRequiredResolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.
routestringOptionalPresent only when the task was submitted with an explicit route parameter; echoes the submitted value.
statusstringRequiredTask status.
queued Queued, not started yet.
handling Being processed.
archiving Processing finished, artifacts being prepared.
success Terminal: completed, artifacts available (output returned).
fail Terminal: failed (error returned).
After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.
creatednumberRequiredTask creation time (Unix seconds).
completednumberRequiredUnix seconds when the task reached a terminal state; fixed to 0 while not terminal.
outputarrayOptional
Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).
Array [ object ]
Array items
urlstringRequiredArtifact URL, directly downloadable.
typestringRequiredCurrent possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.
expireAtnumberRequiredUnix seconds until which the artifact remains accessible; download or transfer before it expires.
errorobjectOptional
Present only when status == fail.
codestringRequiredBusiness error code.
messagestringRequiredError description.
Response examples
Success
{
"code": 200,
"message": "success",
"data": {
"taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
"model": "happyhorse-1-0",
"status": "success",
"created": 1777282033,
"completed": 1777282099,
"output": [
{
"url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
"type": "video",
"expireAt": 1777886899
}
]
}
} Processing (non-terminal)
{
"code": 200,
"message": "success",
"data": {
"taskId": "tk-hiapi-...",
"model": "happyhorse-1-0",
"status": "archiving",
"created": 1777282033,
"completed": 0
}
} Failed
{
"code": 200,
"message": "success",
"data": {
"taskId": "tk-hiapi-...",
"model": "happyhorse-1-0",
"status": "fail",
"created": 1777282033,
"completed": 1777282099,
"error": {
"code": "TASK_FAILED",
"message": "task failed"
}
}
} Articles
View all articles →-
Comparison
Tripo H3.1 Side-by-Side Comparison and Selection Guide: How to Choose Among Three 3D Generation Paths and How to Save
A developer-oriented trade-off between pricing and capability, starting from input form, geometric refinement, and PBR/texture switches
-
Tutorial
Tripo H3.1 Practical Application Scenarios: 5 High-Value Use Cases and Implementation Essentials
From text-to-3D to multiview reconstruction: choosing the right mode and parameters by business scenario
-
Guide
Tripo H3.1 Getting Started Guide: Choosing Among Three Input Modes, Parameters, and Pricing
A practical guide for developers on 3D generation integration decisions and cost control