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% | 99.49% | 98.87% | 97.03% | 924ms | 11.0s | 55 tps | 262K | $0.450 / $3.00 | |
| Healthy | 100% | 99.31% | 98.13% | 99.03% | 1.01s | 3.50s | 60 tps | 262K | $0.500 / $3.60 | |
Phalaphala | Healthy | 100% | 98.36% | 99.16% | 98.96% | 1.48s | 4.65s | 39 tps | 262K | $0.550 / $3.50 |
Alibabaalibaba | No data | — | 98.05% | 99.50% | 99.75% | 1.88s | 4.40s | 34 tps | 262K | $0.390 / $2.34 |
| No data | — | 95.35% | 97.40% | 97.36% | 1.55s | 4.81s | 55 tps | 262K | $0.550 / $3.50 | |
DigitalOceandigitalocean | No data | — | 94.85% | 91.58% | 93.81% | 1.55s | 14.2s | 14 tps | 131K | $0.550 / $3.50 |
| No data | — | 92.04% | 88.99% | 86.46% | 2.21s | 3.75s | 79 tps | 262K | $0.600 / $3.60 | |
| No data | — | — | — | — | — | — | — | 262K | $0.500 / $3.50 | |
Novitanovita | No data | — | 94.93% | 97.65% | 98.62% | 1.50s | 3.60s | 34 tps | 262K | $0.600 / $3.60 |
StreamLakestreamlake | No data | — | 96.63% | 98.89% | 97.38% | 1.13s | 3.49s | 57 tps | 256K | $0.600 / $3.60 |
Venicevenice | No data | — | 89.73% | 95.56% | 93.64% | 823ms | 5.40s | 52 tps | 128K | $0.750 / $4.50 |
- DeepInfra100%Healthy24h 99.49%
- 7d
- 98.87%
- 30d
- 97.03%
- p50
- 924ms
- p99
- 11.0s
- Throughput
- 55 tps
- Context
- 262K
- $/Mtok
- $0.450 / $3.00
deepinfra/fp8fp8 - Parasail100%Healthy24h 99.31%
- 7d
- 98.13%
- 30d
- 99.03%
- p50
- 1.01s
- p99
- 3.50s
- Throughput
- 60 tps
- Context
- 262K
- $/Mtok
- $0.500 / $3.60
parasail/fp8fp8 - Phala100%Healthy24h 98.36%
- 7d
- 99.16%
- 30d
- 98.96%
- p50
- 1.48s
- p99
- 4.65s
- Throughput
- 39 tps
- Context
- 262K
- $/Mtok
- $0.550 / $3.50
phala - No data24h 98.05%
- 7d
- 99.50%
- 30d
- 99.75%
- p50
- 1.88s
- p99
- 4.40s
- Throughput
- 34 tps
- Context
- 262K
- $/Mtok
- $0.390 / $2.34
alibaba - No data24h 95.35%
- 7d
- 97.40%
- 30d
- 97.36%
- p50
- 1.55s
- p99
- 4.81s
- Throughput
- 55 tps
- Context
- 262K
- $/Mtok
- $0.550 / $3.50
atlas-cloud/fp8fp8 - No data24h 94.85%
- 7d
- 91.58%
- 30d
- 93.81%
- p50
- 1.55s
- p99
- 14.2s
- Throughput
- 14 tps
- Context
- 131K
- $/Mtok
- $0.550 / $3.50
digitalocean - No data24h 92.04%
- 7d
- 88.99%
- 30d
- 86.46%
- p50
- 2.21s
- p99
- 3.75s
- Throughput
- 79 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 94.93%
- 7d
- 97.65%
- 30d
- 98.62%
- p50
- 1.50s
- p99
- 3.60s
- Throughput
- 34 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.60
novita - No data24h 96.63%
- 7d
- 98.89%
- 30d
- 97.38%
- p50
- 1.13s
- p99
- 3.49s
- Throughput
- 57 tps
- Context
- 256K
- $/Mtok
- $0.600 / $3.60
streamlake - No data24h 89.73%
- 7d
- 95.56%
- 30d
- 93.64%
- p50
- 823ms
- p99
- 5.40s
- Throughput
- 52 tps
- Context
- 128K
- $/Mtok
- $0.750 / $4.50
venice
Measured 1m 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 · 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