ModelStream LogoModelStream Logo
Models
Video API
Image API
Chat API
Audio API
Studio
Pricing
Docs
Menu
IntroductionQuickstartAPI KeysUse with Hermes AgentUse with OpenClaw
Model ListBilling Guide
ModelStream

Video API

  • Seedance 2.0
  • Happyhorse 1.0
  • Vidu Q3
  • Kling V3.0
  • Veo 3.1
  • Wan 2.7
  • More Video Models →

Image API

  • GPT Image 2
  • Nano Banana 2
  • Seedream 5.0
  • Imagen 4
  • Qwen Image 2.0
  • Z-Image Turbo
  • More Image Models →

Audio API

  • Suno Music
  • Qwen3 TTS Flash
  • More Audio Models →

Chat API

  • GLM-5.2
  • Claude Opus 4.8
  • Gemini 3.5 Flash
  • Qwen 3.7 Max
  • GPT 5.5
  • More Chat Models →

About Us

  • Privacy Policy
  • Terms of Service
  • Support
  • Enterprise

© 2026 ModelStream Inc. All rights reserved.

API Documentation
API Reference
3D Generation
Generate 3D Model

Generate 3D Model

Loading models...

Create a 3D generation task (text/image/multiview to 3D). The "type" field selects the model and request shape; parameters vary per model.

https://api.modelstream.ai
POST/tripo/v2/openapi/task

Authentication

BearerAuth
AuthenticationBearer <token>

All API requests must be authenticated using a Bearer token in the Authorization header. Please ensure your API key is active.Authorization: Bearer sk-xxxxxx

Parameter Location: Header Param

Request Body

application/json

Due to parameter differences across provider models, we recommend referring to the complete form parameter instructions during the specific model trial. The form view intuitively shows parameter types, and the JSON view reveals the exact parameters requested.

type*string

Tripo task type. Acts as the model identifier and selects the request shape: text_to_model / image_to_model / multiview_to_model / refine_model / text_to_image / generate_image / generate_multiview_image / edit_multiview_image.

Required
Enum/Options:
"text_to_model""image_to_model""multiview_to_model""refine_model""text_to_image""generate_image""generate_multiview_image""edit_multiview_image"
prompt?string

Text prompt. Required for text_to_model / text_to_image.

file?object

Single input image for image_to_model. { type: jpg|png|webp, url }.

type?string
url?string
files?array

Positional multiview images for multiview_to_model: [front, left, back, right]. Use {} to skip a non-front slot.

model_version?string

Tripo model version, e.g. v3.0-20250812.

face_limit?integer

Target face count of the generated mesh.

texture?boolean

Whether to generate texture.

pbr?boolean

Whether to generate PBR materials.

texture_quality?string

Texture quality.

Enum/Options:
"standard""detailed"
quad?boolean

Output quad-topology mesh instead of triangles.

auto_size?boolean

Auto-scale the model to real-world size.

style?string

Stylization preset.

draft_model_task_id?string

Source task id referenced by refine_model.

original_task_id?string

Source task id referenced by multiview_to_model / edit_multiview_image.

Response Parameters

application/json
200apiDocs.responses.successCreateTripoTask
code?integer
data?object
task_id?string

System task id; poll it via GET /tripo/v2/openapi/task/{task_id}.

400apiDocs.responses.badRequestParams
error?object

Parameter description for Error

message?string

Error Message

type?string

Error Type

param?string

Related Parameters

code?string

Error Code

curl -X POST "https://api.modelstream.ai/tripo/v2/openapi/task" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
  "type": "text_to_model",
  "prompt": "a cute cartoon robot, vibrant colors",
  "model_version": "v3.0-20250812",
  "texture": true,
  "pbr": true,
  "texture_quality": "standard",
  "face_limit": 10000
}'
{
  "code": 0,
  "data": {
    "task_id": "string"
  }
}