Overview
each::sense uses Server-Sent Events (SSE) for real-time streaming. This enables progressive AI reasoning display, live generation updates, and workflow execution monitoring.
Each event follows the SSE specification:
The stream terminates with:
Enabling Streaming
Set stream: true in your request (this is the default):
Event Categories
Event Flow: Simple Generation
When using /v1/chat/completions, events are wrapped in OpenAI-compatible chunks with each::labs extensions in the eachlabs field:
Timeouts
Last modified on May 28, 2026