Hunyuan 3d V3.1 Text To 3d Rapid API Documentation

Hunyuan 3d V3.1 Text To 3d Rapid API Documentation

Playground

Try it on WaveSpeedAI!

Hunyuan 3D V3.1 Rapid is a fast text-to-3D generation model that quickly creates 3D models from text descriptions. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Hunyuan 3D V3.1 Rapid is Tencent’s fast text-to-3D generation model that creates high-quality 3D models from text descriptions. Simply describe any object — the model generates a complete 3D mesh with textures in seconds. Perfect for rapid prototyping, game assets, e-commerce visualization, and 3D content creation.


Why Choose This?

  • Text-driven generation Create complete 3D models from natural language descriptions — no images or 3D expertise required.

  • Rapid generation Fast processing delivers 3D assets quickly for rapid iteration and prototyping.

  • High-quality output Produces detailed 3D meshes with accurate geometry and textures.

  • Prompt Enhancer Built-in tool to automatically improve your descriptions for better 3D results.

  • Ultra-affordable Just $0.0225 per generation — cost-effective for high-volume workflows.


Parameters

ParameterRequiredDescription
promptYesText description of the 3D object to generate

How to Use

  1. Write your prompt — describe the object you want to create (shape, style, details, pose).
  2. Use Prompt Enhancer (optional) — refine your description for better results.
  3. Run — submit and download your 3D model.

Pricing

OutputCost
Per 3D model$0.0225

Billing Rules

  • Flat rate: $0.0225 per generation
  • No additional charges for mesh complexity or texture quality

Best Use Cases

  • Game Development — Quickly generate 3D assets from concept descriptions.
  • Prototyping — Rapidly visualize object ideas in 3D before production.
  • E-commerce — Create 3D product models for interactive experiences.
  • AR/VR Content — Generate 3D assets for augmented and virtual reality applications.
  • 3D Printing — Generate printable 3D models from text descriptions.
  • Creative Exploration — Experiment with 3D concepts without modeling skills.

Pro Tips

  • Be specific about shape, style, pose, and details in your prompt.
  • Include style keywords like “cartoon style”, “realistic”, “low poly”, or “high detail”.
  • Describe the pose or orientation for character models (e.g., “standing pose”, “T-pose”).
  • Use the Prompt Enhancer to automatically refine vague descriptions.
  • Start with simple objects and iterate to more complex designs.

Notes

  • Prompt is the only required field.
  • Output format is a 3D mesh with textures.
  • More detailed prompts generally produce better results.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan-3d-v3.1/text-to-3d-rapid" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-Text description of the 3D content to generate (max 200 UTF-8 characters)

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.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
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

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
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to poll for the prediction result
data.statusstringStatus: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.