Status

Status

Measured from Bangkok, published whether or not it flatters us.

Continuously measured Per-model metrics From Bangkok

Public metrics

Not yet live

This page will carry time-to-first-token and tokens-per-second per model, measured continuously from Bangkok by the same benchmark that sets our routing defaults. Publishing numbers we do not measure would be worse than publishing none, so it stays empty until the measurements are real.

What will show here

When the numbers are real.

  • Time-to-first-token (TTFT) per model, measured continuously.
  • Tokens-per-second (TPS) under the same benchmark harness.
  • Availability / error signals, not just happy-path latency.
  • The same measurements that feed our routing defaults — not a separate marketing probe.

In the meantime

Create a key, or read how routing and streaming work today.