Qwen3.6 35B A3B
qwen/qwen3.6-35b-a3b
Compare with Qwen3.6 27B, Qwen-Plus, Qwen3.6 Flash
CompareQwen3.6 35B A3B
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
AtlasCloudatlas-cloud/fp8fp8 | Healthy | 100% | 99.82% | 759ms | 7.02s | 101 tps | 262K | $0.186 / $1.11 |
DeepInfradeepinfra/fp8fp8 | Healthy | 100% | 96.23% | 623ms | 6.54s | 23 tps | 262K | $0.100 / $0.950 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 100% | 98.55% | 1.92s | 21.9s | 41 tps | 262K | $0.200 / $1.60 |
AkashMLakashml/fp8fp8 | Healthy | 99.93% | 99.70% | 764ms | 7.03s | 49 tps | 262K | $0.140 / $1.00 |
Venicevenice/fp8fp8 | Healthy | 99.81% | 99.83% | 667ms | 2.08s | 150 tps | 256K | $0.098 / $0.950 |
Parasailparasail/fp8fp8 | Healthy | 99.75% | 99.31% | 883ms | 9.53s | 47 tps | 262K | $0.150 / $1.00 |
CoreWeavecoreweave/fp8fp8 | Healthy | 99.60% | 99.65% | 414ms | 7.06s | 87 tps | 262K | $0.250 / $1.25 |
Io Netio-net/fp8fp8 | Healthy | 97.30% | 99.10% | 1.34s | 10.0s | 37 tps | 262K | $0.190 / $1.19 |
Phalaphala | Down | 77.40% | 99.16% | 1.53s | 15.3s | 60 tps | 262K | $0.200 / $1.27 |
- AtlasCloud100%Healthy24h 99.82%
- p50
- 759ms
- p99
- 7.02s
- Throughput
- 101 tps
- Context
- 262K
- $/Mtok
- $0.186 / $1.11
atlas-cloud/fp8fp8 - DeepInfra100%Healthy24h 96.23%
- p50
- 623ms
- p99
- 6.54s
- Throughput
- 23 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.950
deepinfra/fp8fp8 - SiliconFlow100%Healthy24h 98.55%
- p50
- 1.92s
- p99
- 21.9s
- Throughput
- 41 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.60
siliconflow/fp8fp8 - AkashML99.93%Healthy24h 99.70%
- p50
- 764ms
- p99
- 7.03s
- Throughput
- 49 tps
- Context
- 262K
- $/Mtok
- $0.140 / $1.00
akashml/fp8fp8 - Venice99.81%Healthy24h 99.83%
- p50
- 667ms
- p99
- 2.08s
- Throughput
- 150 tps
- Context
- 256K
- $/Mtok
- $0.098 / $0.950
venice/fp8fp8 - Parasail99.75%Healthy24h 99.31%
- p50
- 883ms
- p99
- 9.53s
- Throughput
- 47 tps
- Context
- 262K
- $/Mtok
- $0.150 / $1.00
parasail/fp8fp8 - CoreWeave99.60%Healthy24h 99.65%
- p50
- 414ms
- p99
- 7.06s
- Throughput
- 87 tps
- Context
- 262K
- $/Mtok
- $0.250 / $1.25
coreweave/fp8fp8 - Io Net97.30%Healthy24h 99.10%
- p50
- 1.34s
- p99
- 10.0s
- Throughput
- 37 tps
- Context
- 262K
- $/Mtok
- $0.190 / $1.19
io-net/fp8fp8 - Phala77.40%Down24h 99.16%
- p50
- 1.53s
- p99
- 15.3s
- Throughput
- 60 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.27
phala
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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.