OpenAI compatible API · Attested · Public status
ScaleDown performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for ScaleDown on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
ScaleDownscaledown
33 samples
Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.
| p50 TTFT | 1303 ms |
|---|---|
| p95 TTFT | 7732 ms |
| Effective throughput | — |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| scaledown/extract | 1085 ms | — | 100.00% | 1 provider_error |
8 |
| scaledown/compress | 1303 ms | — | 100.00% | 1 provider_error |
9 |
| scaledown/summarize | 3086 ms | — | 100.00% | — | 7 |
| scaledown/classify | 3400 ms | — | 100.00% | 1 provider_error |
9 |