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% | 98.77% | 97.92% | 96.17% | 1.08s | 9.52s | 83 tps | 262K | $0.260 / $2.08 |
| Degraded | 92.19% | 93.04% | 94.93% | 93.43% | 1.55s | 5.03s | 36 tps | 262K | $0.260 / $2.08 | |
| No data | — | 94.54% | 98.24% | 97.98% | 910ms | 15.5s | 99 tps | 262K | $0.300 / $2.40 | |
| No data | — | — | 99.94% | 99.74% | — | — | — | 262K | $0.290 / $2.40 | |
| No data | — | 99.55% | 99.53% | 99.59% | 2.61s | 7.33s | 47 tps | 262K | $0.400 / $3.20 |
- Alibaba100%Healthy24h 98.77%
- 7d
- 97.92%
- 30d
- 96.17%
- p50
- 1.08s
- p99
- 9.52s
- Throughput
- 83 tps
- Context
- 262K
- $/Mtok
- $0.260 / $2.08
alibaba - SiliconFlow92.19%Degraded24h 93.04%
- 7d
- 94.93%
- 30d
- 93.43%
- p50
- 1.55s
- p99
- 5.03s
- Throughput
- 36 tps
- Context
- 262K
- $/Mtok
- $0.260 / $2.08
siliconflow/fp8fp8 - No data24h 94.54%
- 7d
- 98.24%
- 30d
- 97.98%
- p50
- 910ms
- p99
- 15.5s
- Throughput
- 99 tps
- Context
- 262K
- $/Mtok
- $0.300 / $2.40
atlas-cloud/fp8fp8 - No data24h —
- 7d
- 99.94%
- 30d
- 99.74%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.290 / $2.40
deepinfra/fp4fp4 - No data24h 99.55%
- 7d
- 99.53%
- 30d
- 99.59%
- p50
- 2.61s
- p99
- 7.33s
- Throughput
- 47 tps
- Context
- 262K
- $/Mtok
- $0.400 / $3.20
novita/bf16bf16
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 · 5 endpoints · 50 days with data, 93 endpoint-days below 90%.