Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Tencent / Hunyuan3D

Hunyuan3D 3.1

Text and image to textured 3D assets, with up to eight reference views.

3D generation
availableClosed weights3D generation
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
12 of 26 specification fields collected
3D output formatsOBJ, GLB, STL, USDZ, FBXSee specification notes below
Polygon count3,000–1,500,000 faces; default 500,000See specification notes below
Input billingSee ratesTencent TokenHub
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Input modalities
Text, ImageSource for Input modalities (opens in a new tab)
Output modalities
3D meshSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not collected

No model-specific cache eligibility or cache discount was verified. A shared gateway field or usage counter does not establish support.

Maximum prompt characters
1,024 UTF-8 charactersSource for Maximum prompt characters (opens in a new tab)

Chinese positive prompts are documented. Text and image are normally mutually exclusive; Sketch mode permits both.

Input image limits
Single image: 128–5000 px per side; URL up to 8 MB, Base64 input up to 6 MB; JPG/PNG/JPEG/WebP.Source for Input image limits (opens in a new tab)
Multi-view input
Front input plus left, right, back, top, bottom, left-front and right-front views.Source for Multi-view input (opens in a new tab)

The native API explicitly limits the four additional elevated/diagonal views to 3.1. TokenHub lists all views in a shared table without this qualification.

Polygon count
3,000–1,500,000 faces; default 500,000Source for Polygon count (opens in a new tab)

Custom face_count does not apply to LowPoly mode.

PBR materials
SupportedSource for PBR materials (opens in a new tab)

Optional PBR material generation. Geometry-only mode ignores PBR. An additional charge applies.

Low-poly generation
Not supportedSource for Low-poly generation (opens in a new tab)

The API explicitly says LowPoly is unavailable for 3.1.

Generation modes
Normal: textured geometry, Geometry: untextured mesh, Sketch: line drawing to 3DSource for Generation modes (opens in a new tab)
Output formats
OBJ, GLB, STL, USDZ, FBXSource for Output formats (opens in a new tab)

Default OBJ and GLB; Geometry mode defaults to GLB. An optional result_format selects one additional format.

Task ID lifetime
24 hoursSource for Task ID lifetime (opens in a new tab)

The documented lifetime is for the task ID, not a contractual data-retention policy.

Request limits
3 concurrent tasks by defaultSource for Request limits (opens in a new tab)

Concurrency capacity is not a batch-inference API.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Tencent TokenHub

Provider source (opens in a new tab)
API model ID
hy-3d-3.1
Access
Tencent Cloud account, activated model service and TokenHub API key required. Availability is documented, not confirmed by a paid inference call.
Regions
Guangzhou gateway. Availability on the separate Singapore site is not inferred; site API keys are not interchangeable.
Endpoint caveat
The guide publishes the request and polling schemas but does not state an HTTP submission path. No path is guessed.Source for Endpoint caveat (opens in a new tab)
Multi-view input
Combined images below 100 MB; each below 8 MB; JPG/PNG; each side greater than 128 and less than 5000 px.Source for Multi-view input (opens in a new tab)

This differs from the native API limits and must not be applied to that endpoint.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
3D generationNormal generation1CN¥2.40successful task
3D generationGeometry generation2CN¥1.80successful task
3D generationSketch generation3CN¥3.00successful task
3D generationMulti-view input add-on4CN¥1.20task
3D generationPBR materials add-on4CN¥1.20task
3D generationCustom face count add-on4CN¥1.20task
3D generationSelected result format add-on5CN¥0.60task

Rate conditions

  1. 20 credits at CNY 0.12 per credit, postpaid. Select one base mode; optional features add charges. Failed tasks are not billed. Prepaid package discounts are not applied.
  2. 15 credits at CNY 0.12 per credit, postpaid. Select one base mode; optional features add charges. Failed tasks are not billed. Prepaid package discounts are not applied.
  3. 25 credits at CNY 0.12 per credit, postpaid. Select one base mode; optional features add charges. Failed tasks are not billed. Prepaid package discounts are not applied.
  4. 10 additional credits at CNY 0.12 per credit when the option is used. These charges add to the selected base mode. PBR is ignored for Geometry; custom face count does not apply to LowPoly.
  5. 5 additional credits at CNY 0.12 per credit when the option is used. These charges add to the selected base mode. PBR is ignored for Geometry; custom face count does not apply to LowPoly.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Tencent Cloud AI3D

Provider source (opens in a new tab)
API model ID
3.1

Model parameter on SubmitHunyuanTo3DProJob.

Access
Tencent Cloud AI3D API; signed cloud credentials and active service required. Not invoked during this review.
Regions
Region is a required native API parameter. Eligible deployment regions remain uncollected.
API endpoint URL
https://ai3d.tencentcloudapi.com · Action: SubmitHunyuanTo3DProJob · Version: 2025-05-13Source for API endpoint URL (opens in a new tab)
Multi-view input
Combined encoded images at most 8 MB; at most 6 MB before Base64 encoding. JPG/PNG; each side greater than 128 and less than 5000 px.Source for Multi-view input (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
3D generationNormal generation1CN¥2.40successful task
3D generationGeometry generation2CN¥1.80successful task
3D generationSketch generation3CN¥3.00successful task
3D generationMulti-view input add-on4CN¥1.20task
3D generationPBR materials add-on4CN¥1.20task
3D generationCustom face count add-on4CN¥1.20task
3D generationSelected result format add-on5CN¥0.60task

Rate conditions

  1. 20 credits at CNY 0.12 per credit, postpaid. Select one base mode; optional features add charges. Failed tasks are not billed. Prepaid package discounts are not applied.
  2. 15 credits at CNY 0.12 per credit, postpaid. Select one base mode; optional features add charges. Failed tasks are not billed. Prepaid package discounts are not applied.
  3. 25 credits at CNY 0.12 per credit, postpaid. Select one base mode; optional features add charges. Failed tasks are not billed. Prepaid package discounts are not applied.
  4. 10 additional credits at CNY 0.12 per credit when the option is used. These charges add to the selected base mode. PBR is ignored for Geometry; custom face count does not apply to LowPoly.
  5. 5 additional credits at CNY 0.12 per credit when the option is used. These charges add to the selected base mode. PBR is ignored for Geometry; custom face count does not apply to LowPoly.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Tencent TokenHub

hy-3d-3.1
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
The platform cache guide does not establish this model’s eligibility, TTL or discount.Source for Limits & data boundaries (opens in a new tab)

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Tencent Cloud AI3D

3.1
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Inferred for this named native commercial model service from its official access documentation and comparison with Tencent’s published model-weight inventory. No weight release for this exact service was found in the reviewed inventory. This is not a claim that every Tencent model is closed or that the provider has disclosed the underlying checkpoint. Public Hy3, Hy4, Hy-MT2 and HunyuanImage 3.0 releases are excluded.

Classification evidence (opens in a new tab)

Sources reviewed