Server-Sent Events

Server-Sent Events (SSE) is a standard HTTP-based protocol for server-to-client streaming, where the server pushes events over a long-lived HTTP connection. SSE is simpler than WebSockets — it uses standard HTTP, works through proxies and load balancers without special configuration, and automatically reconnects on disconnection. In AI applications, SSE is commonly used to stream LLM token generation to the client. While it only supports server-to-client communication (unlike WebSocket's bidirectional flow), this is sufficient for most LLM streaming use cases. Many LLM APIs (OpenAI, Anthropic) use SSE as their streaming format.