Qwen3.5 397B A17B
qwen/qwen3.5-397b-a17b
Compare with Qwen3.5-35B-A3B, Qwen3.5-27B, Qwen3.5-122B-A10B
CompareQwen3.5 397B A17B
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 98.64% | 1.84s | 4.94s | 49 tps | 262K | $0.390 / $2.34 |
AtlasCloudatlas-cloud/fp8fp8 | Healthy | 100% | 96.99% | 1.04s | 22.8s | 59 tps | 262K | $0.550 / $3.50 |
DeepInfradeepinfra/fp8fp8 | Healthy | 100% | 98.03% | 486ms | 2.04s | 30 tps | 262K | $0.450 / $3.00 |
DigitalOceandigitalocean | Healthy | 100% | 95.93% | 928ms | 4.82s | 10 tps | 131K | $0.302 / $1.93 |
Novitanovita | Healthy | 100% | 96.41% | 584ms | 5.54s | 52 tps | 262K | $0.600 / $3.60 |
Parasailparasail/fp8fp8 | Healthy | 100% | 99.42% | 721ms | 4.39s | 57 tps | 262K | $0.500 / $3.60 |
GMICloudgmicloud/fp8fp8 | No data | — | 0.00% | — | — | — | 262K | $0.600 / $3.60 |
Phalaphala | No data | — | 97.99% | 1.49s | 5.51s | 14 tps | 262K | $0.550 / $3.50 |
StreamLakestreamlake | No data | — | 98.40% | 1.77s | 3.50s | 73 tps | 256K | $0.600 / $3.60 |
Venicevenice | No data | — | 97.77% | 1.05s | 21.0s | 64 tps | 128K | $0.750 / $4.50 |
- Alibaba100%Healthy24h 98.64%
- p50
- 1.84s
- p99
- 4.94s
- Throughput
- 49 tps
- Context
- 262K
- $/Mtok
- $0.390 / $2.34
alibaba - AtlasCloud100%Healthy24h 96.99%
- p50
- 1.04s
- p99
- 22.8s
- Throughput
- 59 tps
- Context
- 262K
- $/Mtok
- $0.550 / $3.50
atlas-cloud/fp8fp8 - DeepInfra100%Healthy24h 98.03%
- p50
- 486ms
- p99
- 2.04s
- Throughput
- 30 tps
- Context
- 262K
- $/Mtok
- $0.450 / $3.00
deepinfra/fp8fp8 - DigitalOcean100%Healthy24h 95.93%
- p50
- 928ms
- p99
- 4.82s
- Throughput
- 10 tps
- Context
- 131K
- $/Mtok
- $0.302 / $1.93
digitalocean - Novita100%Healthy24h 96.41%
- p50
- 584ms
- p99
- 5.54s
- Throughput
- 52 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.60
novita - Parasail100%Healthy24h 99.42%
- p50
- 721ms
- p99
- 4.39s
- Throughput
- 57 tps
- Context
- 262K
- $/Mtok
- $0.500 / $3.60
parasail/fp8fp8 - GMICloud—No data24h 0.00%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.600 / $3.60
gmicloud/fp8fp8 - Phala—No data24h 97.99%
- p50
- 1.49s
- p99
- 5.51s
- Throughput
- 14 tps
- Context
- 262K
- $/Mtok
- $0.550 / $3.50
phala - StreamLake—No data24h 98.40%
- p50
- 1.77s
- p99
- 3.50s
- Throughput
- 73 tps
- Context
- 256K
- $/Mtok
- $0.600 / $3.60
streamlake - Venice—No data24h 97.77%
- p50
- 1.05s
- p99
- 21.0s
- Throughput
- 64 tps
- Context
- 128K
- $/Mtok
- $0.750 / $4.50
venice
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
4 endpoints reporting no data are omitted from the charts.
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.