API Reference

📝 TODO — this English page is a skeleton. The structure mirrors the Chinese page, which is fully written.

ModelFold's HTTP API is split in two:

Group	Prefix	Auth	Purpose
Model gateway	/v1	API key	Image, video and chat models
Console API	/api	Session token (JWT)	Auth, account, keys, wallet, mail

https://ai.modelfold.online          # current deployment
https://ai.modelfold.online     # production domain (once live)

Model gateway /v1

Method	Path	Description
GET	/v1/models	List available models
POST	/v1/images/generations	Image generation and editing
POST	/v1/videos/generations	Video generation
POST	/v1/chat/completions	Chat completions (OpenAI-compatible)

See the Gateway reference.

Console API /api

Group	Endpoints	Reference
Authentication	/api/auth/*	Auth
Account	/api/account/*	Account
API keys	/api/keys	API keys
Wallet	/api/wallet/*	Wallet
Mail and email	/api/mail/*, /api/email/*	Mail
Health	GET /api/health	—

Response envelope

Success:

{ "ok": true, "...": "endpoint specific" }

Failure:

{ "ok": false, "error": { "type": "insufficient_credits", "message": "..." } }

Rate limits

Scope	Limit
/v1 gateway	60 requests per key per minute
Key creation	30 per account per minute
Register / login	30 per IP per 10 minutes
Password change	30 per account per 10 minutes
Top-up	10 per account per minute
Email flows	10 per IP per 10 minutes
Test mail	5 per account per 10 minutes

Health check

curl https://ai.modelfold.online/api/health

{ "ok": true, "db": "up" }