Meshy V7.1 Text To 3d API Documentation

Meshy V7.1 Text To 3d API Documentation

Playground

Meshy 7.1 Text-to-3D turns text prompts into textured, PBR-ready 3D models with up to 4K geometry resolution for sharper surface detail, plus configurable topology, rigging, and animation for game assets, product visualization, 3D printing, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Meshy 7.1 Text to 3D generates a 3D model directly from a text prompt. Meshy 7.1 focuses on geometric detail: with geometry_resolution set to 2k or 4k, it produces much finer surfaces and sharper silhouettes than standard geometry. Choose preview for untextured geometry or full for a textured model.

Why Choose This?

• Finer geometric detail geometry_resolution goes up to 4k, capturing small surface details and cleaner silhouettes — useful for close-up renders and 3D printing.

• Texture control Generate textured models, enable PBR maps, or guide textures with a prompt or reference image.

• Production geometry controls Adjust topology, target polygon count, symmetry, and remeshing.

• Optional rigging and animation Rig humanoid characters and apply animation presets in the same request.

• Multiple export formats GLB output with FBX, OBJ, and USDZ exports when available.

Parameters

Pricing

Example Costs

Other parameters do not add separate charges.

Pro Tips

• Use 4k geometry for hero assets, close-up renders, and 3D printing; use standard for quick iteration.
• Higher geometry resolution applies to standard geometry; lowpoly and smart-topology ignore it.
• Use texture_prompt to describe materials such as metal, leather, ceramic, fabric, or plastic.
• Enable rigging only for humanoid characters; animation requires rigging.
• Use preview mode to check shape before paying for a full textured run.

Related Models

• Meshy 7.1 Image to 3D — Generate from a single reference image.
• Meshy 7.1 Multi-Image to 3D — Reconstruct from one to four views of the same object.

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",
  "mode": "full",
  "model_type": "standard",
  "topology": "triangle",
  "target_polycount": 30000,
  "should_remesh": true,
  "symmetry_mode": "auto",
  "enable_pbr": false,
  "pose_mode": "a-pose",
  "geometry_resolution": "standard",
  "enable_rigging": false,
  "rigging_height_meters": 1.7,
  "enable_animation": false,
  "animation_action_id": 92
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/meshy/v7.1/text-to-3d" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 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|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters