Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Tripo / VAST / Tripo H

Tripo H2.5

Tripo H2.5 generates detailed 3D assets from text, one image or multiple views. Texture generation is optional and independently versioned.

3D generation
availableClosed weights3D generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
18 of 34 specification fields collected
3D output formatsGLBSee specification notes below
Text input limit1K1,024
Input billingSee ratesTripo native API · text to model
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 input tokens
Not collected
Maximum output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected

Task JSON is not user-defined structured model output.

Streaming
Not collected

Polling and completion webhooks do not establish streamed geometry.

Batch processing
Not collected

POST /tasks/list batches status queries, not model generation or a discounted Batch API.

Fine-tuning
Not collected

Customer weight fine-tuning is not documented.

Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not collected

Prompt caching is not documented.

Authentication
Bearer API key; JSON request body.Source for Authentication (opens in a new tab)
Request quotas
Per-key request limits vary by endpoint. Account-wide 10 concurrent tasks shared within the H generation category. HTTP 429: code 1007 for request limits, 2000 for concurrency.Source for Request quotas (opens in a new tab)

These are category pools, not separate allowances per model. No fixed requests-per-second quota is published here.

Asynchronous generation
SupportedSource for Asynchronous generation (opens in a new tab)

Task ID followed by status polling or webhook; not progressive model-output streaming.

Task refunds
Credits are frozen when a task is created, consumed on success, and released on failure or cancellation.Source for Task refunds (opens in a new tab)
Data retention
Not collected

Task expiry does not establish a retention duration.

Input modalities
Text, ImageSource for Input modalities (opens in a new tab)
Output modalities
3D meshSource for Output modalities (opens in a new tab)
Usage metering
Native USD task prices. Texture quality and optional processing can add charges; not billed by text tokens.Source for Usage metering (opens in a new tab)
PBR materials
SupportedSource for PBR materials (opens in a new tab)

PBR is enabled by default. Geometry generation with pbr=true forces texture=true.

Seed control
Separate model_seed, texture_seed and (text input only) image_seed controls.Source for Seed control (opens in a new tab)
Output transport
Asynchronous task result containing model and preview URLs.Source for Output transport (opens in a new tab)
Output formats
GLBSource for Output formats (opens in a new tab)

GLB is shown in the result example; this is not an exhaustive export-format guarantee. H-series quad generation explicitly forces FBX.

Maximum prompt characters
1,024Source for Maximum prompt characters (opens in a new tab)

Text-to-model prompt; negative_prompt limit 255 characters. These are not token counts.

Input image formats
PNG, JPEG, WebPSource for Input image formats (opens in a new tab)
Image input limits
Single image: 20 MB maximum. Multiview: 2–4 views, front required. At least 256 × 256 pixels recommended.Source for Image input limits (opens in a new tab)

Multiview contract independently specifies view count/order but no numeric per-file size limit.

Reference images
Multiview order: front, left, back, right. Use view-key objects, four positional strings with empty skipped views, or one prior multiview task_id object. Do not mix formats.Source for Reference images (opens in a new tab)
Mesh topology and face count
500,000 triangle faces in standard mode. Ultra and advanced topology controls are not supported on H2.5.Source for Mesh topology and face count (opens in a new tab)
Texture resolution
Default Texture 2.5. Advanced texture-quality controls have conflicting compatibility notes.Source for Texture resolution (opens in a new tab)
Required request fields
For geometry without textures, set both texture=false and pbr=false. Both default true, and PBR forces texture on.Source for Required request fields (opens in a new tab)

Access & pricing

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

Tripo native API · text to model

Provider source (opens in a new tab)
API model ID
v2.5-20250123

Value of model for this operation; geometry and texture version strings can coincide without identifying the same model.

Access
POST https://openapi.tripo3d.ai/v3/generation/text-to-model with JSON and Bearer API key.
Regions
Processing region not verified
Authentication
Bearer API key; JSON request body.Source for Authentication (opens in a new tab)
Request quotas
Per-key request limits vary by endpoint. Account-wide 10 concurrent tasks shared within the H generation category. HTTP 429: code 1007 for request limits, 2000 for concurrency.Source for Request quotas (opens in a new tab)

These are category pools, not separate allowances per model. No fixed requests-per-second quota is published here.

Asynchronous generation
SupportedSource for Asynchronous generation (opens in a new tab)

Task ID followed by status polling or webhook; not progressive model-output streaming.

Task refunds
Credits are frozen when a task is created, consumed on success, and released on failure or cancellation.Source for Task refunds (opens in a new tab)
Mesh topology and face count
500,000 triangle faces in standard mode. Ultra and advanced topology controls are not supported on H2.5.Source for Mesh topology and face count (opens in a new tab)
Texture resolution
Default Texture 2.5. Advanced texture-quality controls have conflicting compatibility notes.Source for Texture resolution (opens in a new tab)
PBR materials
SupportedSource for PBR materials (opens in a new tab)

PBR is enabled by default. Geometry generation with pbr=true forces texture=true.

Required request fields
For geometry without textures, set both texture=false and pbr=false. Both default true, and PBR forces texture on.Source for Required request fields (opens in a new tab)
Output formats
GLBSource for Output formats (opens in a new tab)

GLB is shown in the result example; this is not an exhaustive export-format guarantee. H-series quad generation explicitly forces FBX.

Maximum prompt characters
1,024Source for Maximum prompt characters (opens in a new tab)

Text-to-model prompt; negative_prompt limit 255 characters. These are not token counts.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
3D generationGeometry only1$0.10request
3D generationGeometry + standard texture2$0.20request

Rate conditions

  1. 10 credits at the published USD 0.01 per credit. texture=false and pbr=false. No optional processing add-ons.
  2. 20 credits at the published USD 0.01 per credit. Standard geometry and texture; no optional topology add-ons.
Pricing source (opens in a new tab)

Data & enterprise terms

Section 5.2.2 (Paid Users) says inputs and outputs are not used to train, validate, test or improve AI technology. Free-user rights differ. No numeric retention duration or zero-retention guarantee was verified.

Read the service policy (opens in a new tab)

Tripo native API · image to model

Provider source (opens in a new tab)
API model ID
v2.5-20250123

Value of model for this operation; geometry and texture version strings can coincide without identifying the same model.

Access
POST https://openapi.tripo3d.ai/v3/generation/image-to-model with JSON and Bearer API key.
Regions
Processing region not verified
Authentication
Bearer API key; JSON request body.Source for Authentication (opens in a new tab)
Request quotas
Per-key request limits vary by endpoint. Account-wide 10 concurrent tasks shared within the H generation category. HTTP 429: code 1007 for request limits, 2000 for concurrency.Source for Request quotas (opens in a new tab)

These are category pools, not separate allowances per model. No fixed requests-per-second quota is published here.

Asynchronous generation
SupportedSource for Asynchronous generation (opens in a new tab)

Task ID followed by status polling or webhook; not progressive model-output streaming.

Task refunds
Credits are frozen when a task is created, consumed on success, and released on failure or cancellation.Source for Task refunds (opens in a new tab)
Mesh topology and face count
500,000 triangle faces in standard mode. Ultra and advanced topology controls are not supported on H2.5.Source for Mesh topology and face count (opens in a new tab)
Texture resolution
Default Texture 2.5. Advanced texture-quality controls have conflicting compatibility notes.Source for Texture resolution (opens in a new tab)
PBR materials
SupportedSource for PBR materials (opens in a new tab)

PBR is enabled by default. Geometry generation with pbr=true forces texture=true.

Required request fields
For geometry without textures, set both texture=false and pbr=false. Both default true, and PBR forces texture on.Source for Required request fields (opens in a new tab)
Output formats
GLBSource for Output formats (opens in a new tab)

GLB is shown in the result example; this is not an exhaustive export-format guarantee. H-series quad generation explicitly forces FBX.

Input image formats
PNG, JPEG, WebPSource for Input image formats (opens in a new tab)
Maximum input content size
20,000,000Source for Maximum input content size (opens in a new tab)

20 MB single image; decimal byte conversion.

Input image enhancement
enable_image_autofix defaults false. align_image orientation only applies when texture is enabled.Source for Input image enhancement (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
3D generationGeometry only1$0.20request
3D generationGeometry + standard texture2$0.30request

Rate conditions

  1. 20 credits at the published USD 0.01 per credit. texture=false and pbr=false. No optional processing add-ons.
  2. 30 credits at the published USD 0.01 per credit. Standard geometry and texture; no optional topology add-ons.
Pricing source (opens in a new tab)

Data & enterprise terms

Section 5.2.2 (Paid Users) says inputs and outputs are not used to train, validate, test or improve AI technology. Free-user rights differ. No numeric retention duration or zero-retention guarantee was verified.

Read the service policy (opens in a new tab)

Tripo native API · multiview to model

Provider source (opens in a new tab)
API model ID
v2.5-20250123

Value of model for this operation; geometry and texture version strings can coincide without identifying the same model.

Access
POST https://openapi.tripo3d.ai/v3/generation/multiview-to-model with JSON and Bearer API key.
Regions
Processing region not verified
Authentication
Bearer API key; JSON request body.Source for Authentication (opens in a new tab)
Request quotas
Per-key request limits vary by endpoint. Account-wide 10 concurrent tasks shared within the H generation category. HTTP 429: code 1007 for request limits, 2000 for concurrency.Source for Request quotas (opens in a new tab)

These are category pools, not separate allowances per model. No fixed requests-per-second quota is published here.

Asynchronous generation
SupportedSource for Asynchronous generation (opens in a new tab)

Task ID followed by status polling or webhook; not progressive model-output streaming.

Task refunds
Credits are frozen when a task is created, consumed on success, and released on failure or cancellation.Source for Task refunds (opens in a new tab)
Mesh topology and face count
500,000 triangle faces in standard mode. Ultra and advanced topology controls are not supported on H2.5.Source for Mesh topology and face count (opens in a new tab)
Texture resolution
Default Texture 2.5. Advanced texture-quality controls have conflicting compatibility notes.Source for Texture resolution (opens in a new tab)
PBR materials
SupportedSource for PBR materials (opens in a new tab)

PBR is enabled by default. Geometry generation with pbr=true forces texture=true.

Required request fields
For geometry without textures, set both texture=false and pbr=false. Both default true, and PBR forces texture on.Source for Required request fields (opens in a new tab)
Output formats
GLBSource for Output formats (opens in a new tab)

GLB is shown in the result example; this is not an exhaustive export-format guarantee. H-series quad generation explicitly forces FBX.

Input image formats
PNG, JPEG, WebPSource for Input image formats (opens in a new tab)
Reference images
Multiview order: front, left, back, right. Use view-key objects, four positional strings with empty skipped views, or one prior multiview task_id object. Do not mix formats.Source for Reference images (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
3D generationGeometry only1$0.20request
3D generationGeometry + standard texture2$0.30request

Rate conditions

  1. 20 credits at the published USD 0.01 per credit. texture=false and pbr=false. No optional processing add-ons.
  2. 30 credits at the published USD 0.01 per credit. Standard geometry and texture; no optional topology add-ons.
Pricing source (opens in a new tab)

Data & enterprise terms

Section 5.2.2 (Paid Users) says inputs and outputs are not used to train, validate, test or improve AI technology. Free-user rights differ. No numeric retention duration or zero-retention guarantee was verified.

Read the service policy (opens in a new tab)

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.

Tripo native API · text to model

v2.5-20250123
Not verified

No prompt-cache API, eligibility or cached-input price documented.

How it works
Not collected

No prompt-cache API, eligibility or cached-input price documented.

Minimum reusable input
Not collected

No prompt-cache API, eligibility or cached-input price documented.

Lifetime & refresh
Not collected

No prompt-cache API, eligibility or cached-input price documented.

How to enable it
Not collected

No prompt-cache API, eligibility or cached-input price documented.

Usage fields
Not collected

No prompt-cache API, eligibility or cached-input price documented.

Billing rules
Not collected

No prompt-cache API, eligibility or cached-input price documented.

Limits & data boundaries
Not collected

No prompt-cache API, eligibility or cached-input price documented.

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

Caching reviewed 14 Oct 2026

Tripo native API · image to model

v2.5-20250123
Not verified

No prompt-cache API, eligibility or cached-input price documented.

How it works
Not collected

No prompt-cache API, eligibility or cached-input price documented.

Minimum reusable input
Not collected

No prompt-cache API, eligibility or cached-input price documented.

Lifetime & refresh
Not collected

No prompt-cache API, eligibility or cached-input price documented.

How to enable it
Not collected

No prompt-cache API, eligibility or cached-input price documented.

Usage fields
Not collected

No prompt-cache API, eligibility or cached-input price documented.

Billing rules
Not collected

No prompt-cache API, eligibility or cached-input price documented.

Limits & data boundaries
Not collected

No prompt-cache API, eligibility or cached-input price documented.

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

Caching reviewed 14 Oct 2026

Tripo native API · multiview to model

v2.5-20250123
Not verified

No prompt-cache API, eligibility or cached-input price documented.

How it works
Not collected

No prompt-cache API, eligibility or cached-input price documented.

Minimum reusable input
Not collected

No prompt-cache API, eligibility or cached-input price documented.

Lifetime & refresh
Not collected

No prompt-cache API, eligibility or cached-input price documented.

How to enable it
Not collected

No prompt-cache API, eligibility or cached-input price documented.

Usage fields
Not collected

No prompt-cache API, eligibility or cached-input price documented.

Billing rules
Not collected

No prompt-cache API, eligibility or cached-input price documented.

Limits & data boundaries
Not collected

No prompt-cache API, eligibility or cached-input price documented.

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

Caching reviewed 14 Oct 2026

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

Qualified inference from provider-hosted named models and terms restricting recovery of underlying models. Reviewed public VAST repositories publish separate TripoSR, TripoSG and TripoSF weights, not these named H/P/Texture API selections. Internal checkpoint identities and individual weight licenses are not disclosed; this is not exhaustive proof of absence.

Classification evidence (opens in a new tab)

Sources reviewed