GPT Image 2.5 ist LIVE — Flare & Sunburst | Im Bild-Generator ausprobieren →

wavespeed-ai/

Meshy 6 generates high-quality 3D models from text descriptions with accurate geometry and superior texture quality. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-3d
Eingabe
Enable Safety Checker

Bereit

$0.8pro Durchlauf·~12 / $10

BeispieleAlle anzeigen

3D model output

Open preview to inspect the generated asset.

A colossal cathedral guardian beast, a lion-like sacred creature with enormous folded stone wings and a floating halo behind its head. Pale marble armor engraved with gothic patterns, gold inlays, stained-glass details, glowing amber cracks, a regal leonine face, golden horns, luminous eyes, bronze chains and ceremonial bells. Strong silhouette, majestic symmetry, high-detail fantasy 3D collectible, realistic stone, bronze, gold, and glass materials, centered, isolated, no background.

3D model output

Open preview to inspect the generated asset.

A mechanical art sculpture shaped like a sacred phoenix, built from layered brushed metal feathers, polished brass joints, engraved ornamental plates, and delicate clockwork details. Elegant wings partially spread, long flowing tail, glowing core in the chest, subtle patina and wear, museum-quality collectible, strong silhouette, highly detailed fantasy-meets-industrial 3D model, realistic metal materials, centered, isolated, no background.

3D model output

Open preview to inspect the generated asset.

A heavy industrial crane arm, articulated joints, hydraulic cylinders, steel beams, hook assembly, cables and pulleys, weathered paint, grease marks, bolts and welded seams, realistic construction machinery design, high-detail 3D model, centered, isolated, no background.

Ähnliche Modelle

README

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
  • 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)
  • 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

Related Models

Hinweis:Diese Website nutzt KI-Modelle von Drittanbietern. Dokumentationspreise dienen nur als Referenz und können veraltet sein. Die Schaltfläche „Generate“ zeigt eine Schätzung; maßgeblich ist der endgültige Auftragspreis.

Meshy6 Text To 3d API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/meshy6/text-to-3d with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Meshy6 Text To 3d below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "topology": "triangle",
    "target_polycount": 30000,
    "symmetry_mode": "auto",
    "should_remesh": true,
    "enable_pbr": false,
    "ta_pose": false,
    "enable_prompt_expansion": false
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/meshy6/text-to-3d" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; 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' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$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
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/meshy6/text-to-3d";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "topology": "triangle",
        "target_polycount": 30000,
        "symmetry_mode": "auto",
        "should_remesh": true,
        "enable_pbr": false,
        "ta_pose": false,
        "enable_prompt_expansion": false
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "topology": "triangle",
    "target_polycount": 30000,
    "symmetry_mode": "auto",
    "should_remesh": True,
    "enable_pbr": False,
    "ta_pose": False,
    "enable_prompt_expansion": False
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/meshy6/text-to-3d", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout", "deleted"}:
        raise RuntimeError(result)
    time.sleep(2)

Meshy6 Text To 3d API — Frequently asked questions

What is the Meshy6 Text To 3d API?

Meshy6 Text To 3d is a WaveSpeedAI model for 3D asset generation, exposed as a REST API on WaveSpeedAI. Meshy 6 generates high-quality 3D models from text descriptions with accurate geometry and superior texture quality. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Meshy6 Text To 3d API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/meshy6-text-to-3d.

How much does Meshy6 Text To 3d cost per run?

Meshy6 Text To 3d starts at $0.8 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Meshy6 Text To 3d accept?

Key inputs: `prompt`, `enable_pbr`, `enable_prompt_expansion`, `should_remesh`, `symmetry_mode`, `ta_pose`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/meshy6-text-to-3d.

How long does Meshy6 Text To 3d take to generate?

Reported generation time on WaveSpeedAI is around 224 seconds per request. This is an estimate, not a latency guarantee; queue time and input settings can change the total wait. live status is visible in the prediction record.

Can I use Meshy6 Text To 3d outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.

Meshy6 Text to 3D | AI Text-to-3D Model API on WaveSpeedAI