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
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 98.93% | 97.75% | 97.75% | 1.19s | 5.87s | 59 tps | 262K | $0.390 / $2.34 |
StreamLakestreamlake | Healthy | 100% | 96.84% | 97.11% | 97.11% | 2.65s | 5.90s | 37 tps | 256K | $0.600 / $3.60 |
| Healthy | 99.52% | 98.73% | 98.13% | 98.13% | 502ms | 7.81s | 26 tps | 262K | $0.450 / $3.00 | |
Phalaphala | Healthy | 99.51% | 95.04% | 96.17% | 96.17% | 1.55s | 68.0s | 33 tps | 262K | $0.550 / $3.50 |
| Healthy | 99.49% | 97.55% | 97.22% | 97.22% | 802ms | 87.2s | 41 tps | 262K | $0.500 / $3.60 | |
Venicevenice | Healthy | 99.36% | 94.86% | 95.44% | 95.44% | 1.55s | 11.6s | 37 tps | 128K | $0.750 / $4.50 |
| Healthy | 96.33% | 96.80% | 96.02% | 96.02% | 1.62s | 21.6s | 50 tps | 262K | $0.550 / $3.50 | |
DigitalOceandigitalocean | No data | — | 97.50% | 94.16% | 94.16% | 1.14s | 5.36s | 17 tps | 131K | $0.550 / $3.50 |
| No data | — | 0.00% | 0.00% | 0.00% | — | — | — | 262K | $0.600 / $3.60 | |
Novitanovita | No data | — | 97.27% | 95.51% | 95.51% | 1.01s | 6.74s | 13 tps | 262K | $0.600 / $3.60 |
- Alibaba100%Healthy24h 98.93%
- 7d
- 97.75%
- 30d
- 97.75%
- p50
- 1.19s
- p99
- 5.87s
- Throughput
- 59 tps
- Context
- 262K
- $/Mtok
- $0.390 / $2.34
alibaba - StreamLake100%Healthy24h 96.84%
- 7d
- 97.11%
- 30d
- 97.11%
- p50
- 2.65s
- p99
- 5.90s
- Throughput
- 37 tps
- Context
- 256K
- $/Mtok
- $0.600 / $3.60
streamlake - DeepInfra99.52%Healthy24h 98.73%
- 7d
- 98.13%
- 30d
- 98.13%
- p50
- 502ms
- p99
- 7.81s
- Throughput
- 26 tps
- Context
- 262K
- $/Mtok
- $0.450 / $3.00
deepinfra/fp8fp8 - Phala99.51%Healthy24h 95.04%
- 7d
- 96.17%
- 30d
- 96.17%
- p50
- 1.55s
- p99
- 68.0s
- Throughput
- 33 tps
- Context
- 262K
- $/Mtok
- $0.550 / $3.50
phala - Parasail99.49%Healthy24h 97.55%
- 7d
- 97.22%
- 30d
- 97.22%
- p50
- 802ms
- p99
- 87.2s
- Throughput
- 41 tps
- Context
- 262K
- $/Mtok
- $0.500 / $3.60
parasail/fp8fp8 - Venice99.36%Healthy24h 94.86%
- 7d
- 95.44%
- 30d
- 95.44%
- p50
- 1.55s
- p99
- 11.6s
- Throughput
- 37 tps
- Context
- 128K
- $/Mtok
- $0.750 / $4.50
venice - AtlasCloud96.33%Healthy24h 96.80%
- 7d
- 96.02%
- 30d
- 96.02%
- p50
- 1.62s
- p99
- 21.6s
- Throughput
- 50 tps
- Context
- 262K
- $/Mtok
- $0.550 / $3.50
atlas-cloud/fp8fp8 - No data24h 97.50%
- 7d
- 94.16%
- 30d
- 94.16%
- p50
- 1.14s
- p99
- 5.36s
- Throughput
- 17 tps
- Context
- 131K
- $/Mtok
- $0.550 / $3.50
digitalocean - No data24h 0.00%
- 7d
- 0.00%
- 30d
- 0.00%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.600 / $3.60
gmicloud/fp8fp8 - No data24h 97.27%
- 7d
- 95.51%
- 30d
- 95.51%
- p50
- 1.01s
- p99
- 6.74s
- Throughput
- 13 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.60
novita
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
Price changes
- Qwen3.5 397B A17BDigitalOceandigitalocean$0.302 / $1.93 → $0.550 / $3.502026-08-21 03:31 UTC
History
3 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 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.