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 |
|---|---|---|---|---|---|---|---|---|
AkashMLakashml/fp8fp8 | Healthy | 100% | 99.76% | 810ms | 6.88s | 48 tps | 262K | $0.140 / $1.00 |
AtlasCloudatlas-cloud/fp8fp8 | Healthy | 100% | 99.82% | 921ms | 6.39s | 92 tps | 262K | $0.186 / $1.11 |
CoreWeavecoreweave/fp8fp8 | Healthy | 100% | 99.65% | 416ms | 9.06s | 136 tps | 262K | $0.250 / $1.25 |
Parasailparasail/fp8fp8 | Healthy | 100% | 99.69% | 740ms | 8.70s | 42 tps | 262K | $0.150 / $1.00 |
Phalaphala | Healthy | 100% | 99.14% | 1.75s | 15.0s | 97 tps | 262K | $0.200 / $1.27 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 100% | 98.54% | 2.23s | 30.6s | 60 tps | 262K | $0.200 / $1.60 |
Venicevenice/fp8fp8 | Healthy | 100% | 99.83% | 618ms | 2.55s | 148 tps | 256K | $0.098 / $0.950 |
Io Netio-net/fp8fp8 | Healthy | 99.50% | 98.99% | 3.67s | 11.7s | 60 tps | 262K | $0.190 / $1.19 |
DeepInfradeepinfra/fp8fp8 | Degraded | 93.70% | 94.25% | 782ms | 27.6s | 26 tps | 262K | $0.100 / $0.950 |
- AkashML100%Healthy24h 99.76%
- p50
- 810ms
- p99
- 6.88s
- Throughput
- 48 tps
- Context
- 262K
- $/Mtok
- $0.140 / $1.00
akashml/fp8fp8 - AtlasCloud100%Healthy24h 99.82%
- p50
- 921ms
- p99
- 6.39s
- Throughput
- 92 tps
- Context
- 262K
- $/Mtok
- $0.186 / $1.11
atlas-cloud/fp8fp8 - CoreWeave100%Healthy24h 99.65%
- p50
- 416ms
- p99
- 9.06s
- Throughput
- 136 tps
- Context
- 262K
- $/Mtok
- $0.250 / $1.25
coreweave/fp8fp8 - Parasail100%Healthy24h 99.69%
- p50
- 740ms
- p99
- 8.70s
- Throughput
- 42 tps
- Context
- 262K
- $/Mtok
- $0.150 / $1.00
parasail/fp8fp8 - Phala100%Healthy24h 99.14%
- p50
- 1.75s
- p99
- 15.0s
- Throughput
- 97 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.27
phala - SiliconFlow100%Healthy24h 98.54%
- p50
- 2.23s
- p99
- 30.6s
- Throughput
- 60 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.60
siliconflow/fp8fp8 - Venice100%Healthy24h 99.83%
- p50
- 618ms
- p99
- 2.55s
- Throughput
- 148 tps
- Context
- 256K
- $/Mtok
- $0.098 / $0.950
venice/fp8fp8 - Io Net99.50%Healthy24h 98.99%
- p50
- 3.67s
- p99
- 11.7s
- Throughput
- 60 tps
- Context
- 262K
- $/Mtok
- $0.190 / $1.19
io-net/fp8fp8 - DeepInfra93.70%Degraded24h 94.25%
- p50
- 782ms
- p99
- 27.6s
- Throughput
- 26 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.950
deepinfra/fp8fp8
Measured 1m 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.