Qwen2.5 VL 72B Instruct
qwen/qwen2.5-vl-72b-instruct
Compare with Qwen2.5 7B Instruct, Qwen2.5 72B Instruct, Qwen-Plus
Showing only the nebius/fp8 provider · show all 2
CompareQwen2.5 VL 72B Instruct
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Down | 100% | 97.15% | 93.32% | 93.32% | 930ms | 55.7s | 19 tps | 32K | $0.250 / $0.750 |
- Nebius100%Down24h 97.15%
- 7d
- 93.32%
- 30d
- 93.32%
- p50
- 930ms
- p99
- 55.7s
- Throughput
- 19 tps
- Context
- 32K
- $/Mtok
- $0.250 / $0.750
nebius/fp8fp8
Measured 3m 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.