Qwen3 235B A22B Instruct 2507
qwen/qwen3-235b-a22b-2507
Compare with Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B, Qwen3 Next 80B A3B Instruct
CompareQwen3 235B A22B Instruct 2507
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.96% | 448ms | 2.26s | 41 tps | 131K | $0.150 / $0.598 |
AtlasCloudatlas-cloud/fp8fp8 | Healthy | 100% | 99.74% | 1.14s | 20.8s | 32 tps | 131K | $0.200 / $0.880 |
GMICloudgmicloud/fp8fp8 | Healthy | 100% | 99.64% | 1.77s | 4.30s | 25 tps | 262K | $0.350 / $1.40 |
Googlegoogle-vertex/us-south1 | Healthy | 100% | 98.96% | 613ms | 2.44s | 27 tps | 262K | $0.250 / $1.00 |
Nebiusnebius/fp8fp8 | Down | 100% | 92.68% | 461ms | 16.8s | 45 tps | 262K | $0.200 / $0.600 |
Novitanovita/fp8fp8 | Healthy | 100% | 97.78% | 651ms | 43.6s | 29 tps | 131K | $0.090 / $0.580 |
Parasailparasail/fp8fp8 | Healthy | 100% | 98.93% | 624ms | 4.89s | 23 tps | 131K | $0.140 / $0.800 |
StreamLakestreamlake | Healthy | 100% | 99.81% | 1.03s | 9.43s | 25 tps | 128K | $0.210 / $0.840 |
DeepInfradeepinfra/fp8fp8 | Healthy | 98.42% | 95.87% | 380ms | 5.40s | 18 tps | 262K | $0.090 / $0.550 |
Venicevenice/fp8fp8 | Healthy | 98.36% | 94.01% | 609ms | 42.5s | 16 tps | 128K | $0.150 / $0.750 |
- Alibaba100%Healthy24h 99.96%
- p50
- 448ms
- p99
- 2.26s
- Throughput
- 41 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.598
alibaba - AtlasCloud100%Healthy24h 99.74%
- p50
- 1.14s
- p99
- 20.8s
- Throughput
- 32 tps
- Context
- 131K
- $/Mtok
- $0.200 / $0.880
atlas-cloud/fp8fp8 - GMICloud100%Healthy24h 99.64%
- p50
- 1.77s
- p99
- 4.30s
- Throughput
- 25 tps
- Context
- 262K
- $/Mtok
- $0.350 / $1.40
gmicloud/fp8fp8 - Google100%Healthy24h 98.96%
- p50
- 613ms
- p99
- 2.44s
- Throughput
- 27 tps
- Context
- 262K
- $/Mtok
- $0.250 / $1.00
google-vertex/us-south1 - Nebius100%Down24h 92.68%
- p50
- 461ms
- p99
- 16.8s
- Throughput
- 45 tps
- Context
- 262K
- $/Mtok
- $0.200 / $0.600
nebius/fp8fp8 - Novita100%Healthy24h 97.78%
- p50
- 651ms
- p99
- 43.6s
- Throughput
- 29 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.580
novita/fp8fp8 - Parasail100%Healthy24h 98.93%
- p50
- 624ms
- p99
- 4.89s
- Throughput
- 23 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.800
parasail/fp8fp8 - StreamLake100%Healthy24h 99.81%
- p50
- 1.03s
- p99
- 9.43s
- Throughput
- 25 tps
- Context
- 128K
- $/Mtok
- $0.210 / $0.840
streamlake - DeepInfra98.42%Healthy24h 95.87%
- p50
- 380ms
- p99
- 5.40s
- Throughput
- 18 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.550
deepinfra/fp8fp8 - Venice98.36%Healthy24h 94.01%
- p50
- 609ms
- p99
- 42.5s
- Throughput
- 16 tps
- Context
- 128K
- $/Mtok
- $0.150 / $0.750
venice/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.