Summarize
scaledown/summarizeInputOutput
Incident RSSCompare with Extract, GLM 5.3, GLM 5.3 Flash
Showing only the scaledown provider · show all 1
CompareSummarize
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
ScaleDownscaledown | No data | — | 99.13% | 100% | 100% | 1.65s | 23.5s | 166 tps | 1.0M | $0.040 / free |
- No data24h 99.13%
- 7d
- 100%
- 30d
- 100%
- p50
- 1.65s
- p99
- 23.5s
- Throughput
- 166 tps
- Context
- 1.0M
- $/Mtok
- $0.040 / free
scaledown
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 1 endpoint · 1 day with data, none below the red threshold. Tables and charts above are filtered to scaledown.