Status
Live gateway and upstream health, plus aggregate usage.
Gateway
—
Upstream pool
—
Last check
—
Usage
| Window | Requests | Input tokens | Output tokens |
|---|---|---|---|
| All time | — | — | — |
| Today | — | — | — |
Per-model health
Availability and latency come from this deployment's own request log. Time to first token and tokens/second are not measured, so those columns are omitted rather than guessed.
| Model | Family | Availability (30m) | Availability (24h) | Requests (30m) | Avg latency (30m) |
|---|---|---|---|---|---|
| Loading… | |||||
Fetched live from GET /api/v1/stats, GET /health
and GET /api/status/models on every page load.