Meshy 6 Text to 3D API: 3D Model Generation

Meshy 6 Text to 3D API Reference

Endpoint

POST https://api.muapi.ai/api/v1/meshy-6-text-to-3d

Submit a job with your MuApi API key in the x-api-key header, then poll https://api.muapi.ai/api/v1/predictions/{request_id}/result until status is completed.

Parameters

Name	Type	Required	Description
prompt	string	Yes	Text prompt describing the 3D object (max 600 chars).
mode	string	No	Preview is faster/cheaper, full produces final quality.Options: preview, fullDefault: "full"
topology	string	No	Output mesh topology.Options: triangle, quadDefault: "triangle"
target_polycount	int	No	Target polygon count for the output mesh.Default: 30000
should_remesh	boolean	No	Enable remesh phase.Default: true
symmetry_mode	string	No	Symmetry detection mode.Options: off, auto, onDefault: "auto"
enable_pbr	boolean	No	Generate PBR maps.Default: false
enable_prompt_expansion	boolean	No	Automatically enrich the prompt for more detail.Default: false

cURL example

REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/meshy-6-text-to-3d \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"<prompt>"}' | jq -r .request_id)

curl -s https://api.muapi.ai/api/v1/predictions/$REQUEST_ID/result -H "x-api-key: $MUAPI_API_KEY"

Python example

import os, time, requests

API = "https://api.muapi.ai/api/v1"
headers = {"x-api-key": os.environ["MUAPI_API_KEY"]}

r = requests.post(f"{API}/meshy-6-text-to-3d", headers=headers, json={"prompt":"<prompt>"})
request_id = r.json()["request_id"]

while True:
    res = requests.get(f"{API}/predictions/{request_id}/result", headers=headers).json()
    if res["status"] == "completed":
        print(res["outputs"]); break
    if res["status"] == "failed":
        raise RuntimeError(res.get("error"))
    time.sleep(3)

Full docs and agent/MCP integration: llms.txt. Get an API key at muapi.ai/access-keys.