Qwen2.5 72B Instruct
qwen/qwen-2.5-72b-instruct
Compare with Qwen2.5 7B Instruct, Qwen2.5 VL 72B Instruct, Qwen-Plus
CompareQwen2.5 72B Instruct
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
DeepInfradeepinfra/fp8fp8 | Healthy | 100% | 99.95% | 288ms | 4.04s | 30 tps | 33K | $0.360 / $0.400 |
Novitanovita/bf16bf16 | Down | — | 17.84% | — | — | — | 32K | $0.380 / $0.400 |
- DeepInfra100%Healthy24h 99.95%
- p50
- 288ms
- p99
- 4.04s
- Throughput
- 30 tps
- Context
- 33K
- $/Mtok
- $0.360 / $0.400
deepinfra/fp8fp8 - Novita—Down24h 17.84%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 32K
- $/Mtok
- $0.380 / $0.400
novita/bf16bf16
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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.