Image-to-3D API
Turn a single image into a textured 3D mesh through one API — models return hosted GLB files you can drop straight into a game engine, viewer, or pipeline.
2 image-to-3D models available right now — every one runnable in a free playground, through the REST API and JavaScript SDK, or from an AI assistant via MCP.
Image-to-3D models & pricing
| Model | Endpoint | Price |
|---|---|---|
| Rodin by Hyper3D | hyper3d/rodin | $0.4 per output |
| Tripo v2.5 Image-to-3D | tripo3d/tripo/v2.5/image-to-3d | $0.3 per output |
Full catalog on the models page; live per-configuration costs on the pricing page.
Call a image-to-3D model in one request
Every model shares the same request lifecycle: submit to the queue, poll the status URL, fetch the result. Swap the endpoint to switch models — nothing else changes.
cURL
curl -X POST https://queue.modelrunner.run/hyper3d/rodin \
-H "Authorization: Key $MRUN_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "input": { "prompt": "..." } }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }Use image-to-3D models from Claude & Cursor
Connect the ModelRunner MCP server once and your AI assistant can run every image-to-3D model in this table as a tool — authorized via OAuth, results returned as hosted URLs in the conversation.
Claude Code
claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcpFrequently asked questions
What output does an image-to-3D API return?
Image-to-3D models return a URL to a generated mesh file (typically GLB, some also textures), hosted on ModelRunner’s media CDN. Model pages document each model’s exact output fields and show an interactive 3D preview of example generations.
How do I call a image-to-3D model via the API?
Every model shares the same request shape: POST https://queue.modelrunner.run/<owner>/<alias> with an Authorization: Key header and an {"input": {...}} body, then poll the returned status_url and fetch the result from response_url. The JavaScript SDK (@modelrunner/client) wraps this in a single subscribe() call. Each model page shows copy-paste cURL, JavaScript, and Python examples with that model's real inputs.
Can I run image-to-3D models from Claude or Cursor?
Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and every image-to-3D model in the catalog becomes a tool your AI assistant can call with the run_model tool — authorized via OAuth, no API key pasted into config.