Qwen2.5 72B Instruct
qwen/qwen-2.5-72b-instructInputOutput
Compare its 2 providersIncident RSSCompare with Qwen-Plus, Qwen2.5 7B Instruct, Qwen2.5 VL 72B Instruct
Showing only the deepinfra/fp8 provider · show all 2
CompareQwen2.5 72B Instruct
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Down | 88.21% | 98.80% | 98.00% | 98.91% | 948ms | 12.2s | 15 tps | 33K | $0.360 / $0.400 |
- DeepInfra88.21%Down24h 98.80%
- 7d
- 98.00%
- 30d
- 98.91%
- p50
- 948ms
- p99
- 12.2s
- Throughput
- 15 tps
- Context
- 33K
- $/Mtok
- $0.360 / $0.400
deepinfra/fp8fp8
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, averaged over the hour.
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 · 2 endpoints · 49 days with data, 30 endpoint-days below 90%. Tables and charts above are filtered to deepinfra/fp8.