Chat and messages
POST /v1/chat/completions
Create a chat completion with streaming, tool calling, and MCP support
POST /v1/messages
Anthropic-compatible messages API with streaming support
Embeddings and retrieval
POST /v1/embeddings
Generate vector embeddings from text
POST /v1/rerank
Rerank documents by relevance to a query
Audio
POST /v1/audio/transcriptions
Transcribe audio files to text
POST /v1/audio/speech
Generate spoken audio from text
Images
POST /v1/images/generations
Generate images from a text prompt
Platform
GET /v1/models
Return supported model metadata
GET /v1/quota
Check current 5-hour spend window usage