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
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.98% | 99.98% | 99.98% | 441ms | 2.93s | 42 tps | 131K | $0.150 / $0.598 |
| Healthy | 100% | 99.57% | 99.81% | 99.81% | 1.04s | 6.10s | 26 tps | 131K | $0.200 / $0.880 | |
| Healthy | 100% | 99.72% | 99.74% | 99.74% | 1.43s | 3.49s | 30 tps | 262K | $0.350 / $1.40 | |
StreamLakestreamlake | Healthy | 100% | 99.83% | 99.84% | 99.84% | 842ms | 4.18s | 29 tps | 128K | $0.210 / $0.840 |
| Healthy | 99.94% | 99.71% | 99.25% | 99.25% | 522ms | 3.31s | 31 tps | 131K | $0.140 / $0.800 | |
| Healthy | 99.84% | 98.49% | 98.76% | 98.76% | 665ms | 4.88s | 27 tps | 131K | $0.090 / $0.580 | |
Googlegoogle-vertex/us-south1 | Healthy | 99.82% | 98.47% | 98.74% | 98.74% | 442ms | 2.20s | 53 tps | 262K | $0.250 / $1.00 |
| Healthy | 99.59% | 97.62% | 96.40% | 96.40% | 370ms | 4.87s | 23 tps | 262K | $0.090 / $0.550 | |
| Healthy | 99.45% | 97.09% | 95.99% | 95.99% | 579ms | 6.16s | 21 tps | 128K | $0.150 / $0.750 | |
| Healthy | 97.55% | 97.13% | 95.46% | 95.46% | 905ms | 9.63s | 45 tps | 262K | $0.200 / $0.600 |
- Alibaba100%Healthy24h 99.98%
- 7d
- 99.98%
- 30d
- 99.98%
- p50
- 441ms
- p99
- 2.93s
- Throughput
- 42 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.598
alibaba - AtlasCloud100%Healthy24h 99.57%
- 7d
- 99.81%
- 30d
- 99.81%
- p50
- 1.04s
- p99
- 6.10s
- Throughput
- 26 tps
- Context
- 131K
- $/Mtok
- $0.200 / $0.880
atlas-cloud/fp8fp8 - GMICloud100%Healthy24h 99.72%
- 7d
- 99.74%
- 30d
- 99.74%
- p50
- 1.43s
- p99
- 3.49s
- Throughput
- 30 tps
- Context
- 262K
- $/Mtok
- $0.350 / $1.40
gmicloud/fp8fp8 - StreamLake100%Healthy24h 99.83%
- 7d
- 99.84%
- 30d
- 99.84%
- p50
- 842ms
- p99
- 4.18s
- Throughput
- 29 tps
- Context
- 128K
- $/Mtok
- $0.210 / $0.840
streamlake - Parasail99.94%Healthy24h 99.71%
- 7d
- 99.25%
- 30d
- 99.25%
- p50
- 522ms
- p99
- 3.31s
- Throughput
- 31 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.800
parasail/fp8fp8 - Novita99.84%Healthy24h 98.49%
- 7d
- 98.76%
- 30d
- 98.76%
- p50
- 665ms
- p99
- 4.88s
- Throughput
- 27 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.580
novita/fp8fp8 - Google99.82%Healthy24h 98.47%
- 7d
- 98.74%
- 30d
- 98.74%
- p50
- 442ms
- p99
- 2.20s
- Throughput
- 53 tps
- Context
- 262K
- $/Mtok
- $0.250 / $1.00
google-vertex/us-south1 - DeepInfra99.59%Healthy24h 97.62%
- 7d
- 96.40%
- 30d
- 96.40%
- p50
- 370ms
- p99
- 4.87s
- Throughput
- 23 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.550
deepinfra/fp8fp8 - Venice99.45%Healthy24h 97.09%
- 7d
- 95.99%
- 30d
- 95.99%
- p50
- 579ms
- p99
- 6.16s
- Throughput
- 21 tps
- Context
- 128K
- $/Mtok
- $0.150 / $0.750
venice/fp8fp8 - Nebius97.55%Healthy24h 97.13%
- 7d
- 95.46%
- 30d
- 95.46%
- p50
- 905ms
- p99
- 9.63s
- Throughput
- 45 tps
- Context
- 262K
- $/Mtok
- $0.200 / $0.600
nebius/fp8fp8
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
Price changes
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 10:45 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 10:40 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 10:35 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 10:30 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 10:25 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 10:20 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 10:15 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 10:11 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 10:06 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 10:01 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 09:56 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 09:51 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 09:46 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 09:41 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 09:36 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 09:31 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 09:26 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 09:21 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 09:16 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 09:11 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 09:06 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 09:01 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 08:56 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 08:51 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 08:46 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 08:41 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 08:36 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 08:31 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 08:26 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 08:21 UTC
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 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.