Skip to main content

System status

Coverage is stale.

Collection is paused. Latest public event: Aug 21, 2026 (10 days ago).

← Intel index

This coverage is stale.

Last updated May 16, 2026 (about 4 months ago).

people · May 16, 2026

Poolside emphasizes latency metrics for Laguna M.1 and XS.2 via Baseten API

Share the canonical public link.

Share as image

Poolside posted on LinkedIn about production latency for its Laguna models delivered through Baseten. Laguna XS.2 recorded median time-to-first-token of 146 ms and P90 latency of 1.5 seconds. Laguna M.1 recorded median time-to-first-token of 605 ms and P90 latency of 3.9 seconds. The company moved from project kickoff to a production-grade white-labeled API in seven weeks.

Spend governor blocked model creation: provider_circuit_open (lane=dev, provider=together)

Supporting evidence