3D Modeling Agent

Available ActionsEach successful request consumes credits as outlined below.

create_model_from_image^100crcreate_model_from_text^150crrefine_model^150crgetlist

Details

Combined 3D modeling workflow for creating assets from a single source image or from a text prompt, refining text-generated drafts into final textured models, and retrieving task status and download URLs from one tool. Supports configurable topology, polygon count, symmetry handling, texture generation, optional PBR outputs, and humanoid pose hints. Completed tasks return downloadable assets in formats such as GLB, FBX, OBJ, and USDZ, while list and get actions make it possible to track active jobs and retrieve completed outputs before the download links expire.

Use Cases

Image to 3D conversion, text to 3D generation, 3D draft generation, 3D model refinement, model status polling, 3D asset retrieval, product visualization, game asset creation, AR and VR asset generation, 3D prototyping, concept modeling, ecommerce 3D assets, downloadable GLB and FBX generation, PBR-ready 3D models, automated 3D workflows

Connect Your Agent In 5 Min

Watch the setup guide for your platform

Or Install Locally

STDIO connector for Claude Code, Codex, Cursor, Zed, and other LLMs that require STDIO or custom connections. This lightweight connector routes requests to https://api.agentpmt.com/mcp. All tool execution happens in the cloud and the server cannot edit any files on your computer.

npm install -g @agentpmt/mcp-routeragentpmt-setup

curl -X POST "https://api.agentpmt.com/products/purchase" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ********" \
  -d '{
    "product_id": "69496f1bb54506f955d789f2",
    "parameters": {
      "action": "create_model_from_image",
      "image_url": "example_image_url",
      "topology": "triangle",
      "target_polycount": 30000,
      "symmetry_mode": "auto",
      "should_remesh": true,
      "should_texture": true
    }
  }'

import requests
import json

url = "https://api.agentpmt.com/products/purchase"

headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer ********"
}

data = {
    "product_id": "69496f1bb54506f955d789f2",
    "parameters": {
        "action": "create_model_from_image",
        "image_url": "example_image_url",
        "topology": "triangle",
        "target_polycount": 30000,
        "symmetry_mode": "auto",
        "should_remesh": true,
        "should_texture": true
    }
}

response = requests.post(url, headers=headers, json=data)
print(response.status_code)
print(response.json())

const url = "https://api.agentpmt.com/products/purchase";

const headers = {
  "Content-Type": "application/json",
  "Authorization": "Bearer ********"
};

const data = {
  product_id: "69496f1bb54506f955d789f2",
  parameters: {
    "action": "create_model_from_image",
    "image_url": "example_image_url",
    "topology": "triangle",
    "target_polycount": 30000,
    "symmetry_mode": "auto",
    "should_remesh": true,
    "should_texture": true
  }
};

fetch(url, {
  method: "POST",
  headers,
  body: JSON.stringify(data)
})
  .then(response => response.json())
  .then(data => console.log(data))
  .catch(error => console.error("Error:", error));

const axios = require('axios');

const url = "https://api.agentpmt.com/products/purchase";

const headers = {
  "Content-Type": "application/json",
  "Authorization": "Bearer ********"
};

const data = {
  product_id: "69496f1bb54506f955d789f2",
  parameters: {
    "action": "create_model_from_image",
    "image_url": "example_image_url",
    "topology": "triangle",
    "target_polycount": 30000,
    "symmetry_mode": "auto",
    "should_remesh": true,
    "should_texture": true
  }
};

axios.post(url, data, { headers })
  .then(response => {
    console.log(response.status);
    console.log(response.data);
  })
  .catch(error => {
    console.error("Error:", error.message);
  });

Login to view your API and budget keys. The example above uses placeholder values. Sign in to see personalized code with your bearer token.

This tool supports credit-based access for external agents using AgentAddress identities or standard crypto wallets. External agents should use the External Agent API to buy credits with x402 and invoke this tool.

1. Buy Credits

Purchase credits via x402 payment (500 credit minimum, 100 credits = $1).

# Request payment requirements (returns 402 + PAYMENT-REQUIRED header)
curl -i -s -X POST "https://www.agentpmt.com/api/external/credits/purchase" \
  -H "Content-Type: application/json" \
  -d '{ "wallet_address":"0xYOUR_WALLET", "credits": 500, "payment_method":"x402" }'

# Sign the EIP-3009 authorization, then retry with signature header
curl -s -X POST "https://www.agentpmt.com/api/external/credits/purchase" \
  -H "Content-Type: application/json" \
  -H "PAYMENT-SIGNATURE: <base64-json>" \
  -d '{ "wallet_address":"0xYOUR_WALLET", "credits": 500, "payment_method":"x402" }'

2. Create a Session Nonce (nonce used in signed balance/invoke)

curl -s -X POST "https://www.agentpmt.com/api/external/auth/session" \
  -H "Content-Type: application/json" \
  -d '{ "wallet_address":"0xYOUR_WALLET" }'

3. Invoke This Tool

Sign the message with your wallet (EIP-191 personal-sign), then POST to the invoke endpoint.

# Sign this message (wallet MUST be lowercased):
# agentpmt-external
# wallet:0xyourwallet...
# session:<session_nonce>
# request:<request_id>
# action:invoke
# product:69496f1bb54506f955d789f2
# payload:<sha256(canonical_json(parameters))>

curl -s -X POST "https://www.agentpmt.com/api/external/tools/69496f1bb54506f955d789f2/invoke" \
  -H "Content-Type: application/json" \
  -d '{
    "wallet_address": "0xYOUR_WALLET",
    "session_nonce": "<session_nonce>",
    "request_id": "invoke-uuid",
    "signature": "0x<signature>",
    "parameters": {
      "action": "your_action",
      "your_param": "value"
    }
  }'

Credentials

MeshyAI API Key *

API Key from your Meshy Dashboard

api key

Manage credentials in your dashboard.

Actions(5)

create_model_from_image^100cr10 params(1 required)

Create a 3D model from a publicly accessible source image. Returns an asynchronous task id for tracking generation progress and downloading the completed asset.

image_urlrequiredstring

Public image URL or base64 data URI for the source image. JPG, JPEG, and PNG are supported.

topologystring

Mesh topology for the generated model.

Values:

quadtriangle

Default: triangle

target_polycountinteger

Target polygon count for the output mesh.

Default: 30000

Range: 100 - 300000

symmetry_modestring

Symmetry handling mode for the generated model.

Values:

offautoon

Default: auto

should_remeshboolean

Apply topology and polygon-count settings. Leave true for most cases.

Default: true

should_textureboolean

Generate texture maps for the model.

Default: true

enable_pbrboolean

Generate PBR maps including metallic, roughness, and normal outputs when supported.

pose_modestring

Pose hint for humanoid subjects.

Values:

a-poset-pose

texture_promptstring

Optional text guidance for texture generation.

texture_image_urlstring

Optional image URL or data URI to guide texture generation.

create_model_from_text^150cr8 params(1 required)

Create an initial 3D model draft from a text prompt. Use refine_model after the draft succeeds to generate the final textured model.

promptrequiredstring

Text prompt describing the model to generate.

ai_modelstring

Text-to-3D model to use for the draft generation step.

Values:

meshy-5meshy-6latest

Default: latest

topologystring

Mesh topology for the generated draft.

Values:

quadtriangle

Default: triangle

target_polycountinteger

Target polygon count for the output mesh.

Default: 30000

Range: 100 - 300000

symmetry_modestring

Symmetry handling mode for the generated draft.

Values:

offautoon

Default: auto

should_remeshboolean

Apply topology and polygon-count settings. Defaults depend on the selected AI model.

pose_modestring

Pose hint for humanoid subjects.

Values:

a-poset-pose

moderationboolean

Screen text inputs for harmful content.

refine_model^150cr6 params(1 required)

Turn a successful text-generated draft into the final textured 3D model.

source_task_idrequiredstring

Task id returned from create_model_from_text.

ai_modelstring

Text-to-3D model to use for the refine step.

Values:

meshy-5latest

Default: latest

enable_pbrboolean

Generate PBR maps including metallic, roughness, and normal outputs when supported.

texture_promptstring

Optional text guidance for texture generation.

texture_image_urlstring

Optional image URL or data URI to guide texture generation.

moderationboolean

Screen text inputs for harmful content.

get1 param(1 required)

Retrieve the latest task status and any output URLs for a single 3D modeling task.

task_idrequiredstring

Task id returned from a create or refine action.

list0 params

List non-expired saved 3D modeling tasks for the current budget.

No parameters for this action.

Usage Instructions

Usage guidance provided directly by the developer for this product.

3D Modeling

Name: 3D Modeling Agent
Brand: Apoth3osis
SKU: 69496f1bb54506f955d789f2
Price: 1.00 USD
Availability: InStock

Generate 3D models from images or text, refine text-generated drafts into final textured assets, and retrieve saved task results from one tool.

Actions

`get_instructions`

Returns this documentation.

`create_model_from_image`

Creates a new image-to-3D generation task.

Required:

image_url — public image URL or base64 data URI for the source image

Optional:

topology — quad or triangle (default triangle)
target_polycount — integer from 100 to 300000 (default 30000)
symmetry_mode — off, auto, or on (default auto)
should_remesh — boolean (default true)
should_texture — boolean (default true)
enable_pbr — boolean (default false)
pose_mode — "", a-pose, or t-pose
texture_prompt — optional texture guidance prompt, max 600 characters
texture_image_url — optional image URL or data URI for texture guidance

`create_model_from_text`

Creates an initial text-generated 3D model draft. After the draft succeeds, use refine_model to generate the final textured model.

Required:

prompt — text prompt describing the model to generate

Optional:

ai_model — meshy-5, meshy-6, or latest (default latest)
topology — quad or triangle (default triangle)
target_polycount — integer from 100 to 300000 (default 30000)
symmetry_mode — off, auto, or on (default auto)
should_remesh — boolean
pose_mode — "", a-pose, or t-pose
moderation — boolean (default false)

`refine_model`

Turns a successful create_model_from_text task into the final textured model.

Required:

source_task_id — task id returned from create_model_from_text

Optional:

ai_model — meshy-5 or latest (default latest)
enable_pbr — boolean (default false)
texture_prompt — optional texture guidance prompt, max 600 characters
texture_image_url — optional image URL or data URI for texture guidance
moderation — boolean (default false)

`get`

Returns the latest task status and any output URLs.

Required:

task_id

`list`

Lists non-expired saved tasks for the current budget.

Examples

{"action":"create_model_from_image","image_url":"https://example.com/chair.jpg"}

{"action":"create_model_from_text","prompt":"a medieval wooden treasure chest"}

{"action":"refine_model","source_task_id":"task_123","enable_pbr":true}

{"action":"get","task_id":"task_123"}

{"action":"list"}

Response

Creation actions return task_id, status, progress, task_family, task_stage, and settings.

get returns status, progress, timestamps, and model_urls when the task succeeds.

list returns count and models[] with saved task metadata.

Notes

Supported source image formats are JPG, JPEG, and PNG.
Text-generated drafts must succeed before you call refine_model.
Download links expire after the retention window, so retrieve completed assets promptly.

About The Developer

Apoth3osis

★15 stars

Joined Agent Payment: August 14, 2025

We build tools that enable AI agents to excel in the mathematical realm.

Our small team develops experimental and unique solutions in the AI arena, with a strong focus on modular computing for agentic applications and custom model deployment. We have handled projects for a variety of applications across many sectors, from algorithmic trading and financial analysis, to molecular simulations and predictions, to habitat and biodiversity monitoring and wildlife conservation.

3D Modeling Agent

Description