Qwen3.5-122B-A10B
qwen/qwen3.5-122b-a10bInputOutput
Compare its 5 providersIncident RSSCompare with Qwen3.5 397B A17B, Qwen3.5-35B-A3B, Qwen3.5-27B
CompareQwen3.5-122B-A10B
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.63% | 93.27% | 96.00% | 573ms | 2.55s | 108 tps | 262K | $0.260 / $2.08 |
| Degraded | 96.67% | 85.50% | 94.97% | 93.67% | 989ms | 19.7s | 50 tps | 262K | $0.260 / $2.08 | |
| Degraded | — | 95.28% | 97.48% | 98.06% | 3.48s | 9.52s | 12 tps | 262K | $0.300 / $2.40 | |
| No data | — | — | 99.94% | 98.67% | — | — | — | 262K | $0.290 / $2.40 | |
| No data | — | 98.62% | 99.05% | 99.59% | 1.54s | 19.0s | 63 tps | 262K | $0.400 / $3.20 |
- Alibaba100%Healthy24h 99.63%
- 7d
- 93.27%
- 30d
- 96.00%
- p50
- 573ms
- p99
- 2.55s
- Throughput
- 108 tps
- Context
- 262K
- $/Mtok
- $0.260 / $2.08
alibaba - SiliconFlow96.67%Degraded24h 85.50%
- 7d
- 94.97%
- 30d
- 93.67%
- p50
- 989ms
- p99
- 19.7s
- Throughput
- 50 tps
- Context
- 262K
- $/Mtok
- $0.260 / $2.08
siliconflow/fp8fp8 - Degraded24h 95.28%
- 7d
- 97.48%
- 30d
- 98.06%
- p50
- 3.48s
- p99
- 9.52s
- Throughput
- 12 tps
- Context
- 262K
- $/Mtok
- $0.300 / $2.40
atlas-cloud/fp8fp8 - No data24h —
- 7d
- 99.94%
- 30d
- 98.67%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.290 / $2.40
deepinfra/fp4fp4 - No data24h 98.62%
- 7d
- 99.05%
- 30d
- 99.59%
- p50
- 1.54s
- p99
- 19.0s
- Throughput
- 63 tps
- Context
- 262K
- $/Mtok
- $0.400 / $3.20
novita/bf16bf16
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint has no chartable data in this range.
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 · 5 endpoints · 47 days with data, 89 endpoint-days below 90%.