meshy-v7/text-to-3d

text-to-3D

Meshy v7 Text-to 3D API by MESHY

meshy-v7/text-to-3d

Text-to-3d

Meshy v7 Text-to-3D generates a 3D mesh from a text prompt in two stages: a preview that produces the untextured geometry, and a refine that textures a preview you kept. Outputs GLB/OBJ/FBX/STL/USDZ/3MF with optional PBR maps up to 8K, a settable polygon budget, and A/T-pose output for characters.

Meshy v7 Text-to 3D is developed by a third-party provider. Atlas Cloud (operated by Atlas Cloud AI LLC) provides access to it and does not own it. All trademarks belong to their respective owners.

INPUT

Prompt *

Mode

Ultra mode

Should remesh

Additional Settings

OUTPUT

Idle

Your generated 3D model will appear here

Configure your settings and click Run to get started

Your request will cost $0.02 per run. For $10 you can run this model approximately 500 times.

Parameters

Code Example
import requests
import time

# Step 1: Start image generation
generate_url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "meshy-v7/text-to-3d",  # Required. Model name. options: meshy-v7/text-to-3d
    "mode": "full",  # How much of the pipeline to run. options: full | preview
    "prompt": "A beautiful landscape with mountains and lake",  # Required. What the object is
    "ultra_mode": False,  # Higher-fidelity geometry with finer surface detail
    "should_remesh": False,  # Run the remesh phase
    "topology": "triangle",  # Topology of the remeshed output. options: triangle | quad
    "target_polycount": 30000,  # Target face count for the remesh phase: 100-300000, default 30000. (min: 100, max: 300000)
    "decimation_mode": 1,  # Adaptive decimation level, used instead of an exact `target_polycount`. options: 1 | 2 | 3 | 4
    "pose_mode": "",  # Force a rest pose for character meshes. options:  | a-pose | t-pose
    "enable_pbr": False,  # Also generate PBR maps (metallic, roughness, normal) alongside the base colour
    "texture_resolution": "2k",  # Base colour texture resolution: 2k (2048²), 4k (4096²) or 8k (8192²). options: 2k | 4k | 8k
    "texture_prompt": "example_value",  # Extra prompt describing the surface material
    "texture_image": "example_value",  # Reference image guiding the texture, as a public URL, base64 data URI, or asset reference (asset://<ASSET_ID>)
    "target_formats": [
        "glb"
    ],  # Which 3D file formats to return. default: ["glb"]
    "auto_size": False,  # Estimate the object's real-world height with AI vision and scale the model accordingly
    "origin_at": "bottom",  # Where the model origin sits when `auto_size` is on. options: bottom | center
    "alpha_thumbnail": False,  # Also render a transparent-background (RGBA) preview image alongside the normal thumbnail
    "moderation": False,  # Screen the input for harmful content before generating
}

generate_response = requests.post(generate_url, headers=headers, json=data)
generate_result = generate_response.json()
prediction_id = generate_result["data"]["id"]

# Step 2: Poll for result
poll_url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"

def check_status():
    while True:
        response = requests.get(poll_url, headers={"Authorization": "Bearer $ATLASCLOUD_API_KEY"})
        result = response.json()

        if result["data"]["status"] == "completed":
            print("Generated image:", result["data"]["outputs"][0])
            return result["data"]["outputs"][0]
        elif result["data"]["status"] == "failed":
            raise Exception(result["data"]["error"] or "Generation failed")
        else:
            # Still processing, wait 2 seconds
            time.sleep(2)

image_url = check_status()

Install

Install the required package for your language.

pip install requests

Authentication

All API requests require authentication via an API key. You can get your API key from the Atlas Cloud dashboard.

export ATLASCLOUD_API_KEY="your-api-key-here"

HTTP Headers

import os

API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_KEY}"
}

Keep your API key secure

Never expose your API key in client-side code or public repositories. Use environment variables or a backend proxy instead.

Submit a request

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "your-model",
    "prompt": "A beautiful landscape"
}

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

Submit a Request

Submit an asynchronous generation request. The API returns a prediction ID that you can use to check the status and retrieve the result.

POST/api/v1/model/generateImage

Request Body

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}

data = {
    "model": "meshy-v7/text-to-3d",
    "prompt": "A beautiful landscape with mountains and lake"
}

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

print(f"Prediction ID: {result['data']['id']}")
print(f"Status: {result['data']['status']}")

Response

{
  "code": 200,
  "data": {
    "id": "pred_abc123",
    "status": "processing",
    "model": "model-name",
    "created_at": "2025-01-01T00:00:00Z"
  }
}

Check Status

Poll the prediction endpoint to check the current status of your request.

GET/api/v1/model/prediction/{prediction_id}

Polling Example

import requests
import time

prediction_id = "pred_abc123"
url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

while True:
    response = requests.get(url, headers=headers)
    result = response.json()
    status = result["data"]["status"]
    print(f"Status: {status}")

    if status in ["completed", "succeeded"]:
        output_url = result["data"]["outputs"][0]
        print(f"Output URL: {output_url}")
        break
    elif status == "failed":
        print(f"Error: {result['data'].get('error', 'Unknown')}")
        break

    time.sleep(3)

Status Values

processingThe request is still being processed.

completedGeneration is complete. Outputs are available.

succeededGeneration succeeded. Outputs are available.

failedGeneration failed. Check the error field.

Completed Response

{
  "data": {
    "id": "pred_abc123",
    "status": "completed",
    "outputs": [
      "https://storage.atlascloud.ai/outputs/result.png"
    ],
    "metrics": {
      "predict_time": 8.3
    },
    "created_at": "2025-01-01T00:00:00Z",
    "completed_at": "2025-01-01T00:00:10Z"
  }
}

Upload Files

Upload files to Atlas Cloud storage and get a URL you can use in your API requests. Use multipart/form-data to upload.

POST/api/v1/model/uploadMedia

Upload Example

import requests

url = "https://api.atlascloud.ai/api/v1/model/uploadMedia"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

with open("image.png", "rb") as f:
    files = {"file": ("image.png", f, "image/png")}
    response = requests.post(url, headers=headers, files=files)

result = response.json()
download_url = result["data"]["download_url"]
print(f"File URL: {download_url}")

Response

{
  "data": {
    "download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
    "file_name": "image.png",
    "content_type": "image/png",
    "size": 1024000
  }
}

Input Schema

The following parameters are accepted in the request body.

Total: 18Required: 2Optional: 16

modelstringrequired

Model name.

Default: "meshy-v7/text-to-3d"

meshy-v7/text-to-3d

modestring

How much of the pipeline to run. `full` generates the mesh and then textures it, returning a finished textured model from one request. `preview` stops after the mesh, for when you want to judge the shape before paying to texture it.

Default: "full"

fullpreview

promptstringrequired

What the object is. Up to 800 characters. Required when `mode` is `preview`.

ultra_modeboolean

Higher-fidelity geometry with finer surface detail. Takes longer and costs 5 extra credits. Applies to the mesh, so it counts in both modes.

Default: false

should_remeshboolean

Run the remesh phase. Leave off for the highest-quality mesh; turn it on when you need a specific polygon budget via `target_polycount` or `decimation_mode`.

Default: false

topologystring

Topology of the remeshed output. `quad` produces a quad-dominant mesh, `triangle` a decimated triangle mesh. Requires `should_remesh`.

Default: "triangle"

trianglequad

target_polycountinteger

Target face count for the remesh phase: 100-300000, default 30000. Requires `should_remesh`, and is ignored when `decimation_mode` is set.

Default: 30000Min: 100Max: 300000

decimation_modeinteger

Adaptive decimation level, used instead of an exact `target_polycount`. 1 = ultra, 2 = high, 3 = medium, 4 = low polycount. Requires `should_remesh`, and takes priority over `target_polycount`.

1234

pose_modestring

Force a rest pose for character meshes. Empty applies no specific pose.

Default: ""

a-poset-pose

enable_pbrboolean

Also generate PBR maps (metallic, roughness, normal) alongside the base colour. Applies to the texture stage, so only when `mode` is `full`.

Default: false

texture_resolutionstring

Base colour texture resolution: 2k (2048²), 4k (4096²) or 8k (8192²). Applies to the texture stage, so only when `mode` is `full`. 8k costs 5 extra credits.

Default: "2k"

2k4k8k

texture_promptstring

Extra prompt describing the surface material. Up to 800 characters. Applies to the texture stage, so only when `mode` is `full`. Takes priority over `texture_image` when both are given.

texture_imagestring

Reference image guiding the texture, as a public URL, base64 data URI, or asset reference (asset://<ASSET_ID>). Formats: jpg/jpeg/png. Applies to the texture stage, so only when `mode` is `full`.

Format: uri

target_formatsarray[string]

Which 3D file formats to return. Defaults to GLB alone; ask for more only when you need them, since each extra format adds generation and transfer time.

Default: ["glb"]Min items: 1Max items: 6

auto_sizeboolean

Estimate the object's real-world height with AI vision and scale the model accordingly.

Default: false

origin_atstring

Where the model origin sits when `auto_size` is on.

Default: "bottom"

bottomcenter

alpha_thumbnailboolean

Also render a transparent-background (RGBA) preview image alongside the normal thumbnail.

Default: false

moderationboolean

Screen the input for harmful content before generating. A flagged request does not proceed to generation.

Default: false

Example Request Body

{
  "model": "meshy-v7/text-to-3d",
  "mode": "full",
  "prompt": "A beautiful landscape",
  "ultra_mode": false,
  "should_remesh": false,
  "topology": "triangle",
  "target_polycount": 30000,
  "pose_mode": "",
  "enable_pbr": false,
  "texture_resolution": "2k",
  "target_formats": [
    "glb"
  ],
  "auto_size": false,
  "origin_at": "bottom",
  "alpha_thumbnail": false,
  "moderation": false
}

Output Schema

The API returns a prediction response with the generated output URLs.

codeinteger

messagestring

dataunknown

Example Response

{
  "id": "pred_abc123",
  "status": "completed",
  "model": "model-name",
  "outputs": [
    "https://storage.atlascloud.ai/outputs/result.png"
  ],
  "metrics": {
    "predict_time": 8.3
  },
  "created_at": "2025-01-01T00:00:00Z",
  "completed_at": "2025-01-01T00:00:10Z"
}

Atlas Cloud Skills

Atlas Cloud Skills integrates 400+ AI models directly into your AI coding assistant. One command to install, then use natural language to generate images, videos, and chat with LLMs.

Supported Clients

Claude Code

OpenAI Codex

Gemini CLI

Cursor

Windsurf

VS Code

Trae

GitHub Copilot

Cline

Roo Code

Amp

Goose

Replit

40+ supported clients

Install

npx skills add AtlasCloudAI/atlas-cloud-skills

Setup API Key

Get your API key from the Atlas Cloud dashboard and set it as an environment variable.

export ATLASCLOUD_API_KEY="your-api-key-here"

Capabilities

Once installed, you can use natural language in your AI assistant to access all Atlas Cloud models.

Image GenerationGenerate images with models like Nano Banana 2, Z-Image, and more.

Video CreationCreate videos from text or images with Kling, Vidu, Veo, etc.

LLM ChatChat with Qwen, DeepSeek, and other large language models.

Media UploadUpload local files for image editing and image-to-video workflows.

Learn more

github.com/AtlasCloudAI/atlas-cloud-skills

MCP Server

Atlas Cloud MCP Server connects your IDE with 400+ AI models via the Model Context Protocol. Works with any MCP-compatible client.

Supported Clients

Cursor

VS Code

Windsurf

Claude Code

OpenAI Codex

Gemini CLI

Cline

Roo Code

100+ supported clients

Install

npx -y atlascloud-mcp

Configuration

Add the following configuration to your IDE's MCP settings file.

{
  "mcpServers": {
    "atlascloud": {
      "command": "npx",
      "args": [
        "-y",
        "atlascloud-mcp"
      ],
      "env": {
        "ATLASCLOUD_API_KEY": "your-api-key-here"
      }
    }
  }
}

Available Tools

atlas_generate_imageGenerate images from text prompts.

atlas_generate_videoCreate videos from text or images.

atlas_chatChat with large language models.

atlas_list_modelsBrowse 400+ available AI models.

atlas_quick_generateOne-step content creation with auto model selection.

atlas_upload_mediaUpload local files for API workflows.

Learn more

github.com/AtlasCloudAI/mcp-server

API Schema

{
  "info": {
    "title": "AtlasCloud API",
    "version": "1.0.0",
    "description": "The AtlasCloud API."
  },
  "openapi": "3.0.0",
  "paths": {
    "/api/v1/model/generateImage": {
      "post": {
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/Input"
              }
            }
          },
          "required": true
        },
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/PredictionResponse"
                }
              }
            },
            "description": "The request status."
          }
        }
      },
      "x-api-name": "model_run"
    },
    "/api/v1/model/prediction/{request_id}": {
      "get": {
        "parameters": [
          {
            "in": "path",
            "name": "request_id",
            "required": true,
            "schema": {
              "description": "Request ID",
              "type": "string"
            }
          }
        ],
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/PredictionResponse"
                }
              }
            },
            "description": "Result of the request."
          }
        }
      },
      "x-api-name": "model_result"
    }
  },
  "components": {
    "schemas": {
      "Input": {
        "type": "object",
        "properties": {
          "model": {
            "type": "string",
            "description": "Model name.",
            "default": "meshy-v7/text-to-3d",
            "enum": [
              "meshy-v7/text-to-3d"
            ]
          },
          "mode": {
            "type": "string",
            "description": "How much of the pipeline to run. `full` generates the mesh and then textures it, returning a finished textured model from one request. `preview` stops after the mesh, for when you want to judge the shape before paying to texture it.",
            "default": "full",
            "enum": [
              "full",
              "preview"
            ],
            "x-enum-labels": {
              "full": "Mesh + texture",
              "preview": "Mesh only"
            },
            "x-ui-component": "select"
          },
          "prompt": {
            "type": "string",
            "description": "What the object is. Up to 800 characters. Required when `mode` is `preview`.",
            "maxLength": 800,
            "x-ui-component": "textarea"
          },
          "ultra_mode": {
            "type": "boolean",
            "description": "Higher-fidelity geometry with finer surface detail. Takes longer and costs 5 extra credits. Applies to the mesh, so it counts in both modes.",
            "default": false,
            "x-ui-component": "switch"
          },
          "should_remesh": {
            "type": "boolean",
            "description": "Run the remesh phase. Leave off for the highest-quality mesh; turn it on when you need a specific polygon budget via `target_polycount` or `decimation_mode`.",
            "default": false,
            "x-ui-component": "switch"
          },
          "topology": {
            "type": "string",
            "description": "Topology of the remeshed output. `quad` produces a quad-dominant mesh, `triangle` a decimated triangle mesh. Requires `should_remesh`.",
            "default": "triangle",
            "enum": [
              "triangle",
              "quad"
            ],
            "x-ui-component": "select"
          },
          "target_polycount": {
            "type": "integer",
            "description": "Target face count for the remesh phase: 100-300000, default 30000. Requires `should_remesh`, and is ignored when `decimation_mode` is set.",
            "minimum": 100,
            "maximum": 300000,
            "x-ui-component": "slider",
            "default": 30000
          },
          "decimation_mode": {
            "type": "integer",
            "description": "Adaptive decimation level, used instead of an exact `target_polycount`. 1 = ultra, 2 = high, 3 = medium, 4 = low polycount. Requires `should_remesh`, and takes priority over `target_polycount`.",
            "enum": [
              1,
              2,
              3,
              4
            ],
            "x-enum-labels": {
              "1": "Ultra",
              "2": "High",
              "3": "Medium",
              "4": "Low"
            },
            "x-ui-component": "select"
          },
          "pose_mode": {
            "type": "string",
            "description": "Force a rest pose for character meshes. Empty applies no specific pose.",
            "default": "",
            "enum": [
              "",
              "a-pose",
              "t-pose"
            ],
            "x-enum-labels": {
              "": "None"
            },
            "x-ui-component": "select"
          },
          "enable_pbr": {
            "type": "boolean",
            "description": "Also generate PBR maps (metallic, roughness, normal) alongside the base colour. Applies to the texture stage, so only when `mode` is `full`.",
            "default": false,
            "x-ui-component": "switch"
          },
          "texture_resolution": {
            "type": "string",
            "description": "Base colour texture resolution: 2k (2048²), 4k (4096²) or 8k (8192²). Applies to the texture stage, so only when `mode` is `full`. 8k costs 5 extra credits.",
            "default": "2k",
            "enum": [
              "2k",
              "4k",
              "8k"
            ],
            "x-ui-component": "select"
          },
          "texture_prompt": {
            "type": "string",
            "description": "Extra prompt describing the surface material. Up to 800 characters. Applies to the texture stage, so only when `mode` is `full`. Takes priority over `texture_image` when both are given.",
            "maxLength": 800,
            "x-ui-component": "textarea"
          },
          "texture_image": {
            "type": "string",
            "description": "Reference image guiding the texture, as a public URL, base64 data URI, or asset reference (asset://<ASSET_ID>). Formats: jpg/jpeg/png. Applies to the texture stage, so only when `mode` is `full`.",
            "format": "uri",
            "x-format": "image",
            "x-accept": ".jpg,.jpeg,.png",
            "x-ui-component": "uploader"
          },
          "target_formats": {
            "type": "array",
            "description": "Which 3D file formats to return. Defaults to GLB alone; ask for more only when you need them, since each extra format adds generation and transfer time.",
            "items": {
              "type": "string",
              "enum": [
                "glb",
                "obj",
                "fbx",
                "stl",
                "usdz",
                "3mf"
              ]
            },
            "default": [
              "glb"
            ],
            "minItems": 1,
            "maxItems": 6,
            "x-ui-component": "select"
          },
          "auto_size": {
            "type": "boolean",
            "description": "Estimate the object's real-world height with AI vision and scale the model accordingly.",
            "default": false,
            "x-ui-component": "switch"
          },
          "origin_at": {
            "type": "string",
            "description": "Where the model origin sits when `auto_size` is on.",
            "default": "bottom",
            "enum": [
              "bottom",
              "center"
            ],
            "x-ui-component": "select"
          },
          "alpha_thumbnail": {
            "type": "boolean",
            "description": "Also render a transparent-background (RGBA) preview image alongside the normal thumbnail.",
            "default": false,
            "x-ui-component": "switch"
          },
          "moderation": {
            "type": "boolean",
            "description": "Screen the input for harmful content before generating. A flagged request does not proceed to generation.",
            "default": false,
            "x-ui-component": "switch"
          }
        },
        "required": [
          "model",
          "prompt"
        ],
        "allOf": [
          {
            "if": {
              "properties": {
                "mode": {
                  "const": "preview"
                }
              },
              "required": [
                "mode"
              ]
            },
            "then": {
              "properties": {
                "enable_pbr": {
                  "x-hidden": true
                },
                "texture_resolution": {
                  "x-hidden": true
                },
                "texture_prompt": {
                  "x-hidden": true
                },
                "texture_image": {
                  "x-hidden": true
                }
              }
            }
          },
          {
            "if": {
              "properties": {
                "should_remesh": {
                  "const": true
                }
              },
              "required": [
                "should_remesh"
              ]
            },
            "else": {
              "properties": {
                "topology": {
                  "x-hidden": true
                },
                "target_polycount": {
                  "x-hidden": true
                },
                "decimation_mode": {
                  "x-hidden": true
                }
              }
            }
          },
          {
            "if": {
              "properties": {
                "auto_size": {
                  "const": true
                }
              },
              "required": [
                "auto_size"
              ]
            },
            "else": {
              "properties": {
                "origin_at": {
                  "x-hidden": true
                }
              }
            }
          }
        ],
        "x-order-properties": [
          "model",
          "mode",
          "prompt",
          "ultra_mode",
          "should_remesh",
          "topology",
          "target_polycount",
          "decimation_mode",
          "pose_mode",
          "enable_pbr",
          "texture_resolution",
          "texture_prompt",
          "texture_image",
          "target_formats",
          "auto_size",
          "origin_at",
          "alpha_thumbnail",
          "moderation"
        ]
      },
      "PredictionResponse": {
        "type": "object",
        "properties": {
          "code": {
            "type": "integer"
          },
          "message": {
            "type": "string"
          },
          "data": {
            "$ref": "#/components/schemas/PredictionData"
          }
        }
      },
      "PredictionData": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "description": "Unique ID of the generation task."
          },
          "model": {
            "type": "string",
            "description": "Model used for the generation."
          },
          "outputs": {
            "type": "array",
            "description": "Generated results: the 3D model file URL(s) for every requested format, then any texture maps, then the preview image last. Null or empty until the task completes.",
            "items": {
              "type": "string"
            }
          },
          "files": {
            "type": "array",
            "description": "Structured metadata for each entry in `outputs`, in the same order, so a client can tell the GLB apart from the OBJ or a texture map.",
            "items": {
              "type": "object",
              "properties": {
                "url": {
                  "type": "string"
                },
                "type": {
                  "type": "string",
                  "description": "Logical file kind, e.g. GLB, OBJ, FBX, USDZ, STL, 3MF, MTL, TEXTURE_IMAGE, PREVIEW."
                },
                "content_type": {
                  "type": "string"
                },
                "file_name": {
                  "type": "string"
                }
              }
            }
          },
          "thumbnail": {
            "type": "string",
            "description": "Rendered preview image of the generated model."
          },
          "credits_consumed": {
            "type": "number",
            "description": "Meshy credits the upstream task consumed, captured for auditing."
          },
          "urls": {
            "type": "object",
            "properties": {
              "get": {
                "type": "string"
              }
            }
          },
          "status": {
            "type": "string",
            "description": "Current task status, such as created, processing, completed, or failed."
          },
          "created_at": {
            "type": "string",
            "format": "date-time"
          },
          "error": {
            "type": "string",
            "description": "Error message returned when the task fails."
          }
        }
      }
    }
  },
  "servers": [
    {
      "url": "https://api.atlascloud.ai"
    }
  ]
}

LLM-Friendly Prompt Template

# meshy-v7/text-to-3d

> Meshy v7 Text-to-3D generates a 3D mesh from a text prompt in two stages: a preview that produces the untextured geometry, and a refine that textures a preview you kept. Outputs GLB/OBJ/FBX/STL/USDZ/3MF with optional PBR maps up to 8K, a settable polygon budget, and A/T-pose output for characters.


## Overview

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateImage` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `meshy-v7/text-to-3d`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  Model name.
  - Default: `"meshy-v7/text-to-3d"`
  - Options: "meshy-v7/text-to-3d"

- **`mode`** (`string`, _optional_):
  How much of the pipeline to run. `full` generates the mesh and then textures it, returning a finished textured model from one request. `preview` stops after the mesh, for when you want to judge the shape before paying to texture it.
  - Default: `"full"`
  - Options: "full", "preview"

- **`prompt`** (`string`, _required_):
  What the object is. Up to 800 characters. Required when `mode` is `preview`.

- **`ultra_mode`** (`boolean`, _optional_):
  Higher-fidelity geometry with finer surface detail. Takes longer and costs 5 extra credits. Applies to the mesh, so it counts in both modes.
  - Default: `false`

- **`should_remesh`** (`boolean`, _optional_):
  Run the remesh phase. Leave off for the highest-quality mesh; turn it on when you need a specific polygon budget via `target_polycount` or `decimation_mode`.
  - Default: `false`

- **`topology`** (`string`, _optional_):
  Topology of the remeshed output. `quad` produces a quad-dominant mesh, `triangle` a decimated triangle mesh. Requires `should_remesh`.
  - Default: `"triangle"`
  - Options: "triangle", "quad"

- **`target_polycount`** (`integer`, _optional_):
  Target face count for the remesh phase: 100-300000, default 30000. Requires `should_remesh`, and is ignored when `decimation_mode` is set.
  - Default: `30000`
  - Min: 100
  - Max: 300000

- **`decimation_mode`** (`integer`, _optional_):
  Adaptive decimation level, used instead of an exact `target_polycount`. 1 = ultra, 2 = high, 3 = medium, 4 = low polycount. Requires `should_remesh`, and takes priority over `target_polycount`.
  - Options: 1, 2, 3, 4

- **`pose_mode`** (`string`, _optional_):
  Force a rest pose for character meshes. Empty applies no specific pose.
  - Default: `""`
  - Options: "", "a-pose", "t-pose"

- **`enable_pbr`** (`boolean`, _optional_):
  Also generate PBR maps (metallic, roughness, normal) alongside the base colour. Applies to the texture stage, so only when `mode` is `full`.
  - Default: `false`

- **`texture_resolution`** (`string`, _optional_):
  Base colour texture resolution: 2k (2048²), 4k (4096²) or 8k (8192²). Applies to the texture stage, so only when `mode` is `full`. 8k costs 5 extra credits.
  - Default: `"2k"`
  - Options: "2k", "4k", "8k"

- **`texture_prompt`** (`string`, _optional_):
  Extra prompt describing the surface material. Up to 800 characters. Applies to the texture stage, so only when `mode` is `full`. Takes priority over `texture_image` when both are given.

- **`texture_image`** (`string`, _optional_):
  Reference image guiding the texture, as a public URL, base64 data URI, or asset reference (asset://<ASSET_ID>). Formats: jpg/jpeg/png. Applies to the texture stage, so only when `mode` is `full`.

- **`target_formats`** (`array[string]`, _optional_):
  Which 3D file formats to return. Defaults to GLB alone; ask for more only when you need them, since each extra format adds generation and transfer time.
  - Default: `["glb"]`
  - Min items: 1
  - Max items: 6

- **`auto_size`** (`boolean`, _optional_):
  Estimate the object's real-world height with AI vision and scale the model accordingly.
  - Default: `false`

- **`origin_at`** (`string`, _optional_):
  Where the model origin sits when `auto_size` is on.
  - Default: `"bottom"`
  - Options: "bottom", "center"

- **`alpha_thumbnail`** (`boolean`, _optional_):
  Also render a transparent-background (RGBA) preview image alongside the normal thumbnail.
  - Default: `false`

- **`moderation`** (`boolean`, _optional_):
  Screen the input for harmful content before generating. A flagged request does not proceed to generation.
  - Default: `false`



**Required Parameters Example**:

```json
{
  "model": "meshy-v7/text-to-3d",
  "prompt": ""
}
```


**Full Example**:

```json
{
  "model": "meshy-v7/text-to-3d",
  "mode": "full",
  "prompt": "",
  "ultra_mode": false,
  "should_remesh": false,
  "topology": "triangle",
  "target_polycount": 30000,
  "decimation_mode": 0,
  "pose_mode": "",
  "enable_pbr": false,
  "texture_resolution": "2k",
  "texture_prompt": "",
  "texture_image": "",
  "target_formats": [
    "glb"
  ],
  "auto_size": false,
  "origin_at": "bottom",
  "alpha_thumbnail": false,
  "moderation": false
}
```


### Output Schema

The API returns the following output format:


- **`code`** (`integer`, _optional_):

- **`message`** (`string`, _optional_):

- **`data`** (`string`, _optional_):



**Example Response**:

```json
{
  "code": 0,
  "message": "",
  "data": null
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateImage" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "meshy-v7/text-to-3d",
  "mode": "full",
  "prompt": "",
  "ultra_mode": false,
  "should_remesh": false,
  "topology": "triangle",
  "target_polycount": 30000,
  "decimation_mode": 0,
  "pose_mode": "",
  "enable_pbr": false,
  "texture_resolution": "2k",
  "texture_prompt": "",
  "texture_image": "",
  "target_formats": [
    "glb"
  ],
  "auto_size": false,
  "origin_at": "bottom",
  "alpha_thumbnail": false,
  "moderation": false
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/meshy-v7/text-to-3d)

No 3D output

A highly detailed 3D model of a rugged off-road beach buggy, wide all-terrain tires, exposed suspension system, reinforced roll cage, sporty aerodynamic body, detailed steering wheel and cockpit, realistic sand tires and metallic components, durable matte body panels, subtle scratches and dust, designed for extreme beach terrain. Studio-quality 3D modeling, clean topology, physically based materials, realistic proportions, intricate mechanical details, cinematic lighting, dramatic three-quarter view, soft shadows, premium automotive concept visualization, photorealistic, high-end game asset quality, isolated background.

Meshy 7 Text-to-3D

Meshy 7 Text-to-3D turns a written description into a production-ready 3D model. One request gives you a finished textured mesh — or, if you set mode to preview, just the geometry, so you can judge the shape before paying to texture it.

Why Choose This?

One request, a finished model — mode: "full" generates the mesh and textures it in a single call.
Or stop at the shape — mode: "preview" returns the bare mesh for a third of the price, for iterating on silhouettes.
Polygon budgets you control — ask for an exact face count, an adaptive decimation level, or the raw high-detail mesh.
Rigging-ready output — force an A-pose or T-pose so characters land in your animation pipeline without cleanup.
Real PBR textures — base colour plus metallic, roughness and normal maps at up to 8K.
Every common format — GLB, OBJ, FBX, STL, USDZ and 3MF.

The Two Modes

`mode`	What runs	What you get
`full` (default)	mesh generation, then texturing	A textured model, with PBR maps if you asked for them
`preview`	mesh generation only	An untextured mesh

Both are one request and one poll. In full mode the two upstream stages are chained for you — the texture parameters (enable_pbr, texture_resolution, texture_prompt, texture_image) are read from the same request and applied to the texture stage, and the geometry parameters (including ultra_mode, which only affects geometry) apply to the mesh stage.

preview is for iteration, not for staging a later texture pass: there is no way to texture a preview afterwards, so run full when you want the finished asset.

Parameters

Parameter	Required	Description
`model`	Yes	`meshy-v7/text-to-3d`
`mode`	No	`full` (default) for mesh + texture, `preview` for mesh only.
`prompt`	Yes	What the object is, up to 800 characters.
`ultra_mode`	No	Finer surface detail. Slower, +5 credits. Default: `false`
`should_remesh`	No	Run the remesh phase. Default: `false` — leave it off for the best mesh.
`topology`	No	`triangle` (default) or `quad`. Requires `should_remesh`.
`target_polycount`	No	Face count, 100–300000. Default: `30000`. Requires `should_remesh`.
`decimation_mode`	No	Adaptive polycount level `1`–`4` (ultra → low). Requires `should_remesh`; overrides `target_polycount`.
`pose_mode`	No	`a-pose`, `t-pose`, or empty for no forced pose.
`enable_pbr`	No	Also produce metallic / roughness / normal maps. `full` only. Default: `false`
`texture_resolution`	No	`2k` (default), `4k`, or `8k`. `full` only.
`texture_prompt`	No	Describe the surface material, up to 800 characters. `full` only.
`texture_image`	No	A reference image for the texture (URL, data URI, or `asset://<ID>`). `full` only.
`target_formats`	No	Any of `glb`, `obj`, `fbx`, `stl`, `usdz`, `3mf`. Default: `["glb"]`
`auto_size`	No	Scale the model to an AI-estimated real-world height. Default: `false`
`origin_at`	No	`bottom` (default) or `center`, when `auto_size` is on.
`alpha_thumbnail`	No	Also render a transparent-background preview. Default: `false`
`moderation`	No	Screen the input for harmful content before generating. Default: `false`

target_formats defaults to GLB alone rather than every format: each extra format is another file to generate and store, so ask for OBJ/FBX/STL/USDZ/3MF only when your pipeline needs them.

topology, target_polycount and decimation_mode only take effect when should_remesh is on — they configure the remesh phase, so with remeshing off they are ignored upstream.

How to Use

A finished textured model:

curl -X POST "https://api.atlascloud.ai/api/v1/model/generateImage" \
  -H "Authorization: Bearer $AIP_API_KEY" \
  -H "Content-Type: application/json" \
  --data-raw '{
    "model": "meshy-v7/text-to-3d",
    "mode": "full",
    "prompt": "a weathered bronze monster mask with curled horns",
    "texture_prompt": "oxidised bronze with green patina in the crevices",
    "enable_pbr": true,
    "texture_resolution": "4k",
    "target_formats": ["glb"]
  }'

Just the geometry, for iterating on the shape:

curl -X POST "https://api.atlascloud.ai/api/v1/model/generateImage" \
  -H "Authorization: Bearer $AIP_API_KEY" \
  -H "Content-Type: application/json" \
  --data-raw '{
    "model": "meshy-v7/text-to-3d",
    "mode": "preview",
    "prompt": "a weathered bronze monster mask with curled horns",
    "target_formats": ["glb"]
  }'

Generation is asynchronous — poll /api/v1/model/prediction/{request_id} until status is completed, then read the model URLs from outputs. files gives the same URLs with their format and MIME type, and thumbnail is a rendered preview image. A full request runs two upstream stages, so it takes longer to reach completed than a preview one.

Pricing

Billed per request, in Meshy credits:

Request	Credits
`preview`	20
`full` at `2k` / `4k` texture	30
`full` at `8k` texture	35
`ultra_mode`	+5 on top of the above

Failed tasks are not charged — including a full request whose texture stage never starts.

Best Use Cases

Concept iteration — spin through ten silhouettes in preview mode, then re-run the winner in full.
Game-ready props — pin a polygon budget with target_polycount and export straight to GLB or FBX.
Characters for animation — pose_mode: "a-pose" plus topology: "quad" gives a mesh that rigs cleanly.
3D printing — target_formats: ["stl", "3mf"] with auto_size for a physically-scaled model.
AR and product viewers — usdz for Apple Quick Look, glb for the web.

Pro Tips

Describe the object, not the picture: "a cast-iron teapot with a bamboo handle" beats "a photo of a teapot on a table".
Leave should_remesh off unless you need a specific face count — remeshing trades detail for polygon control.
decimation_mode is the easier polygon control of the two: pick a level instead of guessing a number — but turn should_remesh on, or neither applies.
Keep target_formats short. One format returns noticeably faster than six.
preview cannot be textured later — when you have settled on a prompt, re-run it in full.

Notes

prompt and texture_prompt are capped at 800 characters each.
mode and texture_resolution must be spelled exactly as documented (lowercase): a request is rejected rather than silently priced at a different rate.
Only one texture guide applies: when both texture_prompt and texture_image are given, the prompt wins.
symmetry_mode, art_style and is_a_t_pose are deprecated upstream and are not exposed here; use pose_mode for poses.
Generated files are re-hosted on AtlasCloud storage, so the URLs you receive are ours and stay reachable — Meshy itself deletes API assets after a few days.

Meshy 7 Image-to-3D — one image in, a textured model out, in a single request.
Meshy 7 Multi-Image-to-3D — up to four views of the same object for a more faithful reconstruction.

Explore Similar Models

NEW

image-to-3D

Meshy v7 Multi-Image-to-3D

Meshy v7 Multi-Image-to-3D reconstructs one textured 3D model from up to four views of the same object, so the sides and back follow your reference instead of being inferred. Supports independent multi-view texture references and PBR maps up to 8K.

Meshy v7 Image-to-3D

Meshy v7 Image-to-3D reconstructs a textured 3D model from a single image in one request. Outputs GLB/OBJ/FBX/STL/USDZ/3MF with optional PBR maps up to 8K, a settable polygon budget, and optional four-angle preview renders.

GPT Image 2.5 Sunburst Text-to-Image

GPT Image 2.5 Sunburst generates images from natural-language prompts with arbitrary resolutions up to 3840x2160, five quality tiers including xhigh and max, and first-class transparent backgrounds. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

GPT Image 2.5 Sunburst Edit

GPT Image 2.5 Sunburst Edit applies natural-language instructions to up to 16 reference images, with an optional mask, arbitrary resolutions up to 3840x2160, five quality tiers including xhigh and max, and transparent-background output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

GPT Image 2.5 Flare Text-to-Image

GPT Image 2.5 Flare generates images from natural-language prompts with arbitrary resolutions up to 3840x2160, five quality tiers including xhigh and max, and first-class transparent backgrounds. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

GPT Image 2.5 Flare Edit

GPT Image 2.5 Flare Edit applies natural-language instructions to up to 16 reference images, with an optional mask, arbitrary resolutions up to 3840x2160, five quality tiers including xhigh and max, and transparent-background output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Openai GPT Image 2 Text-to-Image

GPT Image 2 text to image is OpenAI's fast, cost-efficient text-to-image generator powered by GPT-5 guidance. Create photorealistic shots, product renders, concept art, and stylized graphics from natural-language prompts (optionally conditioned with an image). Supports custom aspect ratios, seeds, negative prompts, hex color hints, and style presets. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

GPT Image 2 Developer Text-to-Image generates polished visuals from natural-language prompts, with common aspect ratios and 1k, 2k, or supported 4k output tiers. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Seedream v4.7 Edit Sequential

ByteDance Seedream 4.7 image editing model with batch generation support. Produce a coherent set of edited images from reference inputs.

Seedream v4.7 Edit

ByteDance Seedream 4.7 image editing model. Executes edit instructions precisely while preserving identity, lighting and local structure of the source image.

From

$0.03/PIC

One API for All Media AI.

Explore all models

Meshy v7 Text-to 3D API by MESHY

INPUT

OUTPUT

Parameters

Code Example

Install

Authentication

HTTP Headers

Submit a request

Submit a Request

Request Body

Response

Check Status

Polling Example

Status Values

Completed Response

Upload Files

Upload Example

Response

Input Schema

Example Request Body

Output Schema

Example Response

Atlas Cloud Skills

Supported Clients

Install

Setup API Key

Capabilities

MCP Server

Supported Clients

Install

Configuration

Available Tools

API Schema

LLM-Friendly Prompt Template

Meshy 7 Text-to-3D

Why Choose This?

The Two Modes

Parameters

How to Use

Pricing

Best Use Cases

Pro Tips

Notes

Related Models

Explore Similar Models

Meshy v7 Multi-Image-to-3D

Meshy v7 Image-to-3D

GPT Image 2.5 Sunburst Text-to-Image

GPT Image 2.5 Sunburst Edit

GPT Image 2.5 Flare Text-to-Image

GPT Image 2.5 Flare Edit

Openai GPT Image 2 Text-to-Image

Openai GPT Image 2 Edit

GPT Image 2.5 Flare Developer Edit

GPT Image 2.5 Flare Developer Text-to-Image

GPT Image 2.5 Sunburst Developer Edit

GPT Image 2.5 Sunburst Developer Text-to-Image

GPT Image 2 Developer Edit

GPT Image 2 Developer Text-to-Image

Seedream v4.7 Edit Sequential

Seedream v4.7 Edit

One API for All Media AI.

INPUT

OUTPUT

Parameters

Code Example

Install

Authentication

HTTP Headers

Submit a request

Submit a Request

Request Body

Response

Check Status

Polling Example

Status Values

Completed Response

Upload Files

Upload Example