Qwen3.5 397B A17B
qwen/qwen3.5-397b-a17bInputOutput
Compare its 11 providersIncident RSSCompare with Qwen3.5-35B-A3B, Qwen3.5-27B, Qwen3.5-9B
CompareQwen3.5 397B A17B
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 95.34% | 97.34% | 97.36% | 1.36s | 5.78s | 59 tps | 262K | $0.550 / $3.50 | |
| Healthy | 100% | 99.53% | 98.87% | 96.94% | 928ms | 7.23s | 56 tps | 262K | $0.450 / $3.00 | |
DigitalOceandigitalocean | Healthy | 100% | 94.61% | 91.45% | 93.79% | 1.58s | 27.0s | 10 tps | 131K | $0.550 / $3.50 |
| Healthy | 100% | 99.36% | 98.13% | 99.03% | 655ms | 4.32s | 82 tps | 262K | $0.500 / $3.60 | |
Phalaphala | Healthy | 100% | 98.43% | 99.16% | 98.96% | 1.96s | 5.85s | 50 tps | 262K | $0.550 / $3.50 |
StreamLakestreamlake | Healthy | 100% | 96.68% | 98.88% | 97.36% | 1.03s | 4.20s | 65 tps | 256K | $0.600 / $3.60 |
Alibabaalibaba | No data | — | 98.09% | 99.50% | 99.75% | 987ms | 35.7s | 77 tps | 262K | $0.390 / $2.34 |
| No data | — | 93.21% | 89.50% | 86.55% | 1.93s | 5.71s | 83 tps | 262K | $0.600 / $3.60 | |
| No data | — | — | — | — | — | — | — | 262K | $0.500 / $3.50 | |
Novitanovita | No data | — | 94.78% | 97.69% | 98.62% | 1.30s | 2.61s | 73 tps | 262K | $0.600 / $3.60 |
Venicevenice | No data | — | 89.96% | 95.73% | 93.69% | 799ms | 5.08s | 71 tps | 128K | $0.750 / $4.50 |
- AtlasCloud100%Healthy24h 95.34%
- 7d
- 97.34%
- 30d
- 97.36%
- p50
- 1.36s
- p99
- 5.78s
- Throughput
- 59 tps
- Context
- 262K
- $/Mtok
- $0.550 / $3.50
atlas-cloud/fp8fp8 - DeepInfra100%Healthy24h 99.53%
- 7d
- 98.87%
- 30d
- 96.94%
- p50
- 928ms
- p99
- 7.23s
- Throughput
- 56 tps
- Context
- 262K
- $/Mtok
- $0.450 / $3.00
deepinfra/fp8fp8 - DigitalOcean100%Healthy24h 94.61%
- 7d
- 91.45%
- 30d
- 93.79%
- p50
- 1.58s
- p99
- 27.0s
- Throughput
- 10 tps
- Context
- 131K
- $/Mtok
- $0.550 / $3.50
digitalocean - Parasail100%Healthy24h 99.36%
- 7d
- 98.13%
- 30d
- 99.03%
- p50
- 655ms
- p99
- 4.32s
- Throughput
- 82 tps
- Context
- 262K
- $/Mtok
- $0.500 / $3.60
parasail/fp8fp8 - Phala100%Healthy24h 98.43%
- 7d
- 99.16%
- 30d
- 98.96%
- p50
- 1.96s
- p99
- 5.85s
- Throughput
- 50 tps
- Context
- 262K
- $/Mtok
- $0.550 / $3.50
phala - StreamLake100%Healthy24h 96.68%
- 7d
- 98.88%
- 30d
- 97.36%
- p50
- 1.03s
- p99
- 4.20s
- Throughput
- 65 tps
- Context
- 256K
- $/Mtok
- $0.600 / $3.60
streamlake - No data24h 98.09%
- 7d
- 99.50%
- 30d
- 99.75%
- p50
- 987ms
- p99
- 35.7s
- Throughput
- 77 tps
- Context
- 262K
- $/Mtok
- $0.390 / $2.34
alibaba - No data24h 93.21%
- 7d
- 89.50%
- 30d
- 86.55%
- p50
- 1.93s
- p99
- 5.71s
- Throughput
- 83 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.60
gmicloud/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.500 / $3.50
morph/fp4fp4 - No data24h 94.78%
- 7d
- 97.69%
- 30d
- 98.62%
- p50
- 1.30s
- p99
- 2.61s
- Throughput
- 73 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.60
novita - No data24h 89.96%
- 7d
- 95.73%
- 30d
- 93.69%
- p50
- 799ms
- p99
- 5.08s
- Throughput
- 71 tps
- Context
- 128K
- $/Mtok
- $0.750 / $4.50
venice
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, 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 · 11 endpoints · 47 days with data, 210 endpoint-days below 90%.
Price changes
- Qwen3.5 397B A17BDigitalOceandigitalocean$0.550 / $3.50cache read $0.111 → $0.1102026-09-14 15:15 UTC
- Qwen3.5 397B A17BDigitalOceandigitalocean$0.302 → $0.550 / $1.93 → $3.502026-08-21 03:31 UTC