Qwen2.5 72B Instruct
qwen/qwen-2.5-72b-instruct
Compare with Qwen2.5 7B Instruct, Qwen2.5 VL 72B Instruct, Qwen-Plus
Showing only the deepinfra/fp8 provider · show all 2
CompareQwen2.5 72B Instruct
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.78% | 99.72% | 99.72% | 289ms | 1.51s | 30 tps | 33K | $0.360 / $0.400 |
- DeepInfra100%Healthy24h 99.78%
- 7d
- 99.72%
- 30d
- 99.72%
- p50
- 289ms
- p99
- 1.51s
- Throughput
- 30 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.
Throughput
Median tokens per second.