Browse ModelsWavespeed AIMeshy6 Text To 3d

Meshy6 Text To 3d

Meshy6 Text To 3d

Playground

Try it on WavespeedAI!

Meshy 6 generates high-quality 3D models from text descriptions with accurate geometry and superior texture quality.

Features

Meshy 6 Text to 3D

Meshy 6 is the latest text-to-3D generation model featuring best-in-class geometry reconstruction and superior texture generation. Create production-ready 3D models from text descriptions with multiple export formats.

Key Capabilities

  • Text-driven generation - Create 3D models from natural language descriptions
  • Best-in-class geometry - Most accurate geometry reconstruction for detailed 3D models
  • Superior textures - High-quality texture generation with optional PBR maps
  • Multiple formats - Export as GLB, FBX, OBJ, or USDZ
  • Artistic styles - Choose between realistic or sculpture styles
  • Prompt expansion - Optional LLM-powered prompt enhancement for better results

Parameters

Required

  • prompt: Text description of the 3D object (max 600 characters)

Generation Options

  • mode: Generation mode - preview (untextured, faster) or full (textured, default)
  • art_style: Artistic style - realistic or sculpture (default: realistic)
  • enable_prompt_expansion: Use LLM to expand prompt details (default: false)

Geometry Options

  • topology: Mesh topology - quad for smooth surfaces, triangle for detailed geometry (default: triangle)
  • target_polycount: Target polygon count (default: 30000, range: 100-300000)
  • symmetry_mode: Symmetry behavior - off, auto, or on (default: auto)
  • should_remesh: Enable remesh phase for cleaner topology (default: true)
  • ta_pose: Generate in A/T pose for rigging (default: false)

Texture Options

  • enable_pbr: Generate PBR maps including metallic, roughness, and normal (default: false)
  • texture_prompt: Additional text for texture guidance (full mode only)
  • texture_image: Reference image to guide texturing (full mode only)

Output Formats

The model outputs 3D files in multiple formats:

  • GLB - Universal web-ready format
  • FBX - For game engines and 3D software
  • OBJ - Standard interchange format
  • USDZ - Apple AR Quick Look compatible

Pricing

$0.80 per generation

Notes

  • Processing typically takes 5-10 minutes
  • Preview mode is faster but produces untextured models
  • Full mode includes high-quality textures
  • Use prompt expansion for more detailed results from simple descriptions
  • Enable PBR for game-ready assets with material properties
  • Enable A/T pose for characters intended for animation

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/meshy6/text-to-3d" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "art_style": "realistic",
    "topology": "triangle",
    "target_polycount": 30000,
    "symmetry_mode": "auto",
    "should_remesh": true,
    "enable_pbr": false,
    "ta_pose": false,
    "enable_prompt_expansion": false
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-Describe what kind of object the 3D model is. Maximum 600 characters.
art_stylestringNorealisticrealistic, sculptureDesired artistic style of the generated model
topologystringNotrianglequad, triangleSpecify the topology of the generated model. Quad for smooth surfaces, Triangle for detailed geometry.
target_polycountintegerNo30000100 ~ 300000Target polygon count in generated model
symmetry_modestringNoautooff, auto, onControls symmetry behavior of the generated model
should_remeshbooleanNotrue-Enable remesh phase for cleaner topology
enable_pbrbooleanNofalse-Generate PBR maps (metallic, roughness, normal)
ta_posebooleanNofalse-Generate model in A/T pose for rigging
enable_prompt_expansionbooleanNofalse-Use LLM to expand prompt details for better results
texture_promptstringNo--Additional text for texture guidance (full mode only)
texture_imagestringNo--2D image for texture guidance (full mode only)

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction, the ID of the prediction to get
data.modelstringModel ID used for the prediction
data.outputsstringGenerated 3D model outputs in multiple formats.
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2025 WaveSpeedAI. All rights reserved.