Schematron V2 Turbo
inference-net/schematron-v2-turboInputOutput
Compare its 3 providersIncident RSSCompare with Schematron V2 Small, GLM 5.3, DeepSeek V4.1 Flash 1017
Showing only the inference-net/bf16 provider · show all 3
CompareSchematron V2 Turbo
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 100% | 92.32% | 98.51% | 318ms | 1.45s | 139 tps | 128K | $0.030 / $0.150 |
- InferenceNet100%Healthy24h 100%
- 7d
- 92.32%
- 30d
- 98.51%
- p50
- 318ms
- p99
- 1.45s
- Throughput
- 139 tps
- Context
- 128K
- $/Mtok
- $0.030 / $0.150
inference-net/bf16bf16
Measured 2m 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 · 3 endpoints · 51 days with data, 10 endpoint-days below 90%. Tables and charts above are filtered to inference-net/bf16.
Price changes
- Schematron V2 TurboInferenceNetinference-net$0.030 / $0.150cache read — → $0.0302026-09-13 18:25 UTC