Qwen3.5-35B-A3B
qwen/qwen3.5-35b-a3b
Compare with Qwen3.5 397B A17B, Qwen3.5-27B, Qwen3.5-122B-A10B
CompareQwen3.5-35B-A3B
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.40% | 675ms | 21.3s | 80 tps | 262K | $0.163 / $1.30 |
CoreWeavecoreweave/fp8fp8 | Healthy | 100% | 99.92% | 307ms | 6.47s | 216 tps | 262K | $0.250 / $1.25 |
DeepInfradeepinfra/fp8fp8 | Healthy | 100% | 99.07% | 853ms | 2.36s | 51 tps | 262K | $0.140 / $1.00 |
Parasailparasail/fp8fp8 | Healthy | 100% | 99.25% | 653ms | 14.3s | 98 tps | 262K | $0.150 / $1.00 |
Venicevenice | Healthy | 100% | 99.88% | 1.17s | 20.7s | 101 tps | 256K | $0.313 / $1.25 |
AkashMLakashml/fp8fp8 | No data | — | — | — | — | — | 262K | $0.140 / $1.00 |
AtlasCloudatlas-cloud/fp8fp8 | No data | — | 99.78% | 1.09s | 3.19s | 50 tps | 262K | $0.225 / $1.80 |
SiliconFlowsiliconflow/fp8fp8 | No data | — | 95.74% | 1.75s | 7.78s | 28 tps | 262K | $0.240 / $1.80 |
- Alibaba100%Healthy24h 99.40%
- p50
- 675ms
- p99
- 21.3s
- Throughput
- 80 tps
- Context
- 262K
- $/Mtok
- $0.163 / $1.30
alibaba - CoreWeave100%Healthy24h 99.92%
- p50
- 307ms
- p99
- 6.47s
- Throughput
- 216 tps
- Context
- 262K
- $/Mtok
- $0.250 / $1.25
coreweave/fp8fp8 - DeepInfra100%Healthy24h 99.07%
- p50
- 853ms
- p99
- 2.36s
- Throughput
- 51 tps
- Context
- 262K
- $/Mtok
- $0.140 / $1.00
deepinfra/fp8fp8 - Parasail100%Healthy24h 99.25%
- p50
- 653ms
- p99
- 14.3s
- Throughput
- 98 tps
- Context
- 262K
- $/Mtok
- $0.150 / $1.00
parasail/fp8fp8 - Venice100%Healthy24h 99.88%
- p50
- 1.17s
- p99
- 20.7s
- Throughput
- 101 tps
- Context
- 256K
- $/Mtok
- $0.313 / $1.25
venice - AkashML—No data24h —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.140 / $1.00
akashml/fp8fp8 - AtlasCloud—No data24h 99.78%
- p50
- 1.09s
- p99
- 3.19s
- Throughput
- 50 tps
- Context
- 262K
- $/Mtok
- $0.225 / $1.80
atlas-cloud/fp8fp8 - SiliconFlow—No data24h 95.74%
- p50
- 1.75s
- p99
- 7.78s
- Throughput
- 28 tps
- Context
- 262K
- $/Mtok
- $0.240 / $1.80
siliconflow/fp8fp8
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.