Endpoints

Use https://api.model-gate.com for all inference and metadata requests.

Generation

Method	Path	Documentation
POST	/v1/messages	Anthropic Messages
POST	/v1/messages/count_tokens	Count tokens
POST	/v1/chat/completions	OpenAI Chat Completions
POST	/v1/responses	OpenAI Responses
POST	/v1/embeddings	Embeddings
POST	/v1/images/generations	Image generations
POST/GET	/v1/messages/batches...	Claude Message Batches
POST/GET	/v1/files, /v1/batches...	OpenAI-compatible Batch API

Models and account

Method	Path	Documentation
GET	/v1/models	List models and key-specific prices
GET	/v1/models/{id}	Get one model
GET	/v1/balance	Get account balance

Service health

Method	Path	Authentication
GET	/health	None
GET	/health/live	None
GET	/health/ready	None

Only the endpoints listed above are part of the supported public contract. Other /v1/* paths may be passed through for compatibility but can change without notice.