MCP / Models / 3D generation
Hunyuan 3D 3.1 Pro MCP: detailed models from photos
Tencent Hunyuan 3D 3.1 Pro turns a front photo, and up to seven more views, into a detailed textured 3D model with up to 1.5 million faces. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

$ YOUR NEXT RUN
Use Hunyuan 3D 3.1 Pro in your assistant
Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/hunyuan-3d-3-1-pro-image-to-3d.md. Help me connect the FlyMy.AI MCP to this assistant, then run Hunyuan 3D 3.1 Pro (flymyai/hunyuan-3d-3_1-pro-image-to-3d) for this task: Turn the product photo I attach into a textured 3D model with Hunyuan 3D 3.1 Pro and send me the model file.
What Hunyuan 3D 3.1 Pro does
Send image, the front view, and add back_image, left_image, right_image, top_image, bottom_image, left_front_image and right_front_image for a more faithful back and sides. generate_type Geometry returns a plain white model, enable_pbr adds metallic, roughness and normal maps, and face_count sets the polygon budget from 40,000 to 1,500,000. Outputs: model (GLB), preview and seed. It takes no text and does not rig.
Guide: AI 3D model generator API: Tripo, Meshy and Hunyuan 3D
Hunyuan 3D 3.1 Pro inputs
Every input of flymyai/hunyuan-3d-3_1-pro-image-to-3d as its live schema lists them. Returns model (array), preview (array), seed (string).
| Input | Type, values and default |
|---|---|
# image | file required Allowed: image file, as a URL or upload The front view of the object: a link or an upload (JPG, PNG or WebP, 128-5000 px, up to 8 MB); one object on a simple background, filling more than half of the frame |
# back_image | file optional Allowed: image file, as a URL or upload Optional view of the back; any extra view adds $0.15 once |
# left_image | file optional Allowed: image file, as a URL or upload Optional view of the left side; any extra view adds $0.15 once |
# right_image | file optional Allowed: image file, as a URL or upload Optional view of the right side; any extra view adds $0.15 once |
# top_image | file optional Allowed: image file, as a URL or upload Optional view of the top; any extra view adds $0.15 once |
# bottom_image | file optional Allowed: image file, as a URL or upload Optional view of the bottom; any extra view adds $0.15 once |
# left_front_image | file optional Allowed: image file, as a URL or upload Optional view of the left-front, at 45 degrees; any extra view adds $0.15 once |
# right_front_image | file optional Allowed: image file, as a URL or upload Optional view of the right-front, at 45 degrees; any extra view adds $0.15 once |
# generate_type | string optional Allowed: Normal, Geometry Default: Normal Normal makes a textured model, Geometry a plain white model without textures |
# enable_pbr | boolean optional Default: false Make PBR materials (metallic, roughness, normal maps); +$0.15, ignored for Geometry |
# face_count | integer optional Allowed: 40000 to 1500000 Target number of faces, 40000-1500000; left out the model uses about 500000; setting it adds $0.15 |
Ask your agent
Requests to paste as they are, once the FlyMy.AI MCP is connected.
flymyai/hunyuan-3d-3_1-pro-image-to-3dflymyai/hunyuan-3d-3_1-pro-image-to-3dflymyai/hunyuan-3d-3_1-pro-image-to-3dHunyuan 3D 3.1 Pro price
From $0.375 per run, depending on enable_pbr, back_image, left_image, right_image, top_image, bottom_image, left_front_image, right_front_image and face_count. A run at the default settings costs $0.375. A run costs $0.375 to $0.825, depending on enable_pbr and back_image and left_image and right_image and top_image and bottom_image and left_front_image and right_front_image and face_count. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.
Call Hunyuan 3D 3.1 Pro from code
The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.
From an agent, through the MCP
The agent calls get_model_schema, then run_model with:
{
"endpoint_id": "flymyai/hunyuan-3d-3_1-pro-image-to-3d",
"input": {
"image": "https://example.com/photo.jpg"
}
}From your code, over HTTP
Form fields, not JSON; files go as uploads or public URLs. The answer is a prediction_id; read the result at https://api.flymy.ai/api/v1/flymyai/hunyuan-3d-3_1-pro-image-to-3d/predict/async/result/?request_id=<prediction_id>.
curl -X POST https://api.flymy.ai/api/v1/flymyai/hunyuan-3d-3_1-pro-image-to-3d/predict/async/ \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-F "image=@photo.jpg"Questions about Hunyuan 3D 3.1 Pro
Do I need a Tencent API key for Hunyuan 3D 3.1 Pro?
No. Hunyuan 3D 3.1 Pro runs on FlyMy.AI's account, so you need no Tencent key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.
How much does Hunyuan 3D 3.1 Pro cost?
From $0.375 per run, depending on enable_pbr, back_image, left_image, right_image, top_image, bottom_image, left_front_image, right_front_image and face_count. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.
How do I use Hunyuan 3D 3.1 Pro in Claude Code, Codex or Cursor?
Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Turn the product photo I attach into a textured 3D model with Hunyuan 3D 3.1 Pro and send me the model file." Your agent reads the inputs with get_model_schema and runs flymyai/hunyuan-3d-3_1-pro-image-to-3d with run_model.
What does Hunyuan 3D 3.1 Pro need as input?
Hunyuan 3D 3.1 Pro requires image; it also takes 10 optional inputs, each listed on this page with its allowed values and default.
Can I call Hunyuan 3D 3.1 Pro from my own code?
Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/hunyuan-3d-3_1-pro-image-to-3d/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.
Go to the source
From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.





