Auto rig

Live

Add a skeleton to a humanoid model so it can move. Get a rigged FBX and GLB, plus walk and run clips.

from $0.585Rigged FBX + GLB · Walk and run clips · Any humanoid model

Auto rig

from $0.585

Input

Model linkmodel_urlA public https link to the GLB to rig, or to an FBX from our 3D model tool.

A public https link to a GLB of a humanoid, best in a T-pose. An FBX also works if our 3D model tool made it.

Walk and run clipsanimationsAnimation clips made for the rigged model.No extra charge

Example

Example output

Loading animation…

GLB Thumbnail Rigged FBX Walking (FBX) clip Running (FBX) clip

How the 3D pipeline works

The same steps we use to make characters for our own games.

01T-pose checkA quick look at your picture. If it is not a strict front T-pose with a closed, neutral mouth on a plain background, it is redrawn that way, keeping the same character. Arms held out keep the hands clean.
023D modelA textured, game-ready mesh made from the T-pose picture, with PBR materials and the lighting taken out. Characters and props get their own triangle budgets.
03RigA skeleton fitted to the character so it can move, with walk and run clips when you ask. You get FBX for game engines and GLB for the web.

Run all three steps in one call:3D characters

Call Auto rig from your code

Each 3D tool is its own endpoint. Every call returns a task: poll it until it finishes. A failed run is not charged.

POSThttps://api.opennan.com/v1/3d/rig

POST/v1/3d/charactersPicture or prompt to a rigged character.
POST/v1/3d/tposeAny character picture to a front T-pose.
POST/v1/3d/modelsPicture or prompt to a textured model.
GET/v1/tasks/{id}Progress and output files.
GET/v1/models?category=3d3D engines and quality tiers, with prices

Get an API key
Create a key in the console. It uses the same balance as the playground.
Create a key

Send your first request

The same request the playground sends. Set OPENNAN_KEY to your key.

curl https://api.opennan.com/v1/3d/rig \
  -H "Authorization: Bearer $OPENNAN_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model_url":"https://example.com/character.glb","animations":true}'

# Then poll until "status" is "succeeded" or "failed":
curl https://api.opennan.com/v1/tasks/<task id> -H "Authorization: Bearer $OPENNAN_KEY"

Poll the task
The call answers right away with a task id. Ask for the task until it finishes:
GEThttps://api.opennan.com/v1/tasks/{id}
queued
Waiting for a worker
running
Being made
succeeded
Done: outputs[].url holds the files
failed
Failed: you are not charged

Errors and how to fix them

401Missing or wrong key
Send the header Authorization: Bearer with a key from the console.
402Balance too low
Add credit in Billing, then send the same call again.
400A value is not accepted
Read error.message: it names the field. Use a value from the parameter table.
429Too many requests
Wait a few seconds and try again, waiting longer after each 429.

Add Opennan to your AI app

One install gives your AI every Opennan tool: video, images, chat, voice, music, sound effects, 3D, captions and dubbing. Pick your app and follow the steps.

MCP serverhttps://api.opennan.com/v1/mcp

Works in the Codex CLI, the Codex app and the Codex IDE extension: they share ~/.codex/config.toml. If the app or IDE does not see OPENNAN_KEY, use the config.toml option with your key in it. Codex asks before each tool call: approve it to go on.

Get an API key
Create a key in the console. It starts with sk- and uses the same balance as the website.
Create a key

Save your key as OPENNAN_KEY

# macOS / Linux (zsh shown; bash: ~/.bashrc)
echo 'export OPENNAN_KEY="sk-..."' >> ~/.zshrc
source ~/.zshrc

# Windows (PowerShell), then open a new terminal
setx OPENNAN_KEY "sk-..."

3
Install the Opennan plugin: the server plus a skill that teaches your AI to pick models, confirm prices and wait for results
```
codex plugin marketplace add Opennan/opennan-ai-plugin
codex plugin add opennan@opennan
```

Or add only the server

codex mcp add opennan --url https://api.opennan.com/v1/mcp --bearer-token-env-var OPENNAN_KEY

Or add this to ~/.codex/config.toml

[mcp_servers.opennan]
url = "https://api.opennan.com/v1/mcp"
http_headers = { Authorization = "Bearer sk-..." }

4
Check that opennan is listed
```
codex mcp list
```
Restart Codex, then ask for anything
“Make a 5 second video of rain on a neon street, a song to go with it and a poster image.”

Replace sk-... with your own key and keep it private: anyone who has it can spend your balance. Your app can list the tools before you add a key; making anything needs one.

This tool from your AI

Once Opennan is added, your AI calls this tool with arguments like these.

Tool: rig_3d_model
Example arguments: { "model_url": "https://example.com/character.glb", "animations": true }

Auto rig: questions

How much does Auto rig cost?

You pay per run, at the price shown before you start.

How do I call it from my code?

Send POST https://api.opennan.com/v1/3d/rig with your API key. It answers with a task id: ask https://api.opennan.com/v1/tasks/{id} until the task succeeds or fails.

Can my AI agent use it?

Yes. Add the MCP server https://api.opennan.com/v1/mcp and call the rig_3d_model tool, or point your agent at https://api.opennan.com/llms.txt.

What happens if a run fails?

A failed run is not charged. You pay only for results.

Why does the picture need a T-pose?

Arms held straight out keep the hands apart from the body, so the model gets clean hands and the rig bends at the right joints. Arms down or an A-pose often fuse the hands into the clothes, and a smile gets painted into the texture. That is why a picture that is not a T-pose is redrawn first, keeping the character the same.

Which files do I get?

GLB for the web, game engines and 3D apps, FBX for Roblox Studio, Unity, Unreal and Blender, and a thumbnail. Rigged runs add walk and run clips.

Auto rig

Input

Output

How the 3D pipeline works

Call Auto rig from your code

Get an API key

Send your first request

Poll the task

Errors and how to fix them

Add Opennan to your AI app

This tool from your AI

Auto rig: questions