← Qwen3 235B A22B Instruct 2507
Qwen3 235B A22B Instruct 2507: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.46% | 98.60% | 98.55% | 1.28s | 16.6s | 49 tps | 262K | $0.087 / $0.350◆ (best) | |
StreamLakestreamlake | Healthy | 100%◆ (best) | 99.31% | 98.64% | 98.81% | 589ms | 10.5s | 55 tps | 128K | $0.210 / $0.840 |
| Healthy | 100%◆ (best) | 97.45% | 90.29% | 93.77% | 628ms | 6.38s | 25 tps | 128K | $0.150 / $0.750 | |
Googlegoogle-vertex/us-south1 | Healthy | 99.97% | 99.87% | 99.61% | 99.82% | 744ms | 16.1s | 22 tps | 262K | $0.220 / $0.880 |
| Healthy | 99.95% | 98.08% | 82.03% | 89.72% | 460ms | 7.92s | 23 tps | 262K | $0.090 / $0.550 | |
| Healthy | 99.53% | 99.82% | 99.89%◆ (best) | 99.84%◆ (best) | 424ms◆ (best) | 5.59s | 36 tps | 131K | $0.140 / $0.800 | |
| Healthy | 99.40% | 97.43% | 96.66% | 97.79% | 723ms | 29.5s | 44 tps | 131K | $0.090 / $0.580 | |
Alibabaalibaba | Healthy | 96.43% | 98.69% | 97.72% | 99.00% | 478ms | 5.42s◆ (best) | 58 tps◆ (best) | 131K | $0.150 / $0.598 |
| Down | 18.18% | 89.82% | 92.20% | 91.46% | 5.01s | 45.9s | 15 tps | 262K | $0.200 / $0.600 | |
| No data | — | — | — | 98.27% | — | — | — | 131K | $0.200 / $0.880 | |
PrimeIntellectprimeintellect | No data | — | — | 95.44% | 95.44% | — | — | — | 262K | $0.250 / $1.00 |
- GMICloud100%◆ (best)Healthy24h 99.46%
- 7d
- 98.60%
- 30d
- 98.55%
- p50
- 1.28s
- p99
- 16.6s
- Throughput
- 49 tps
- Context
- 262K
- $/Mtok
- $0.087 / $0.350◆ (best)
gmicloud/fp8fp8 - StreamLake100%◆ (best)Healthy24h 99.31%
- 7d
- 98.64%
- 30d
- 98.81%
- p50
- 589ms
- p99
- 10.5s
- Throughput
- 55 tps
- Context
- 128K
- $/Mtok
- $0.210 / $0.840
streamlake - Venice100%◆ (best)Healthy24h 97.45%
- 7d
- 90.29%
- 30d
- 93.77%
- p50
- 628ms
- p99
- 6.38s
- Throughput
- 25 tps
- Context
- 128K
- $/Mtok
- $0.150 / $0.750
venice/fp8fp8 - Google99.97%Healthy24h 99.87%
- 7d
- 99.61%
- 30d
- 99.82%
- p50
- 744ms
- p99
- 16.1s
- Throughput
- 22 tps
- Context
- 262K
- $/Mtok
- $0.220 / $0.880
google-vertex/us-south1 - DeepInfra99.95%Healthy24h 98.08%
- 7d
- 82.03%
- 30d
- 89.72%
- p50
- 460ms
- p99
- 7.92s
- Throughput
- 23 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.550
deepinfra/fp8fp8 - Parasail99.53%Healthy24h 99.82%
- 7d
- 99.89%◆ (best)
- 30d
- 99.84%◆ (best)
- p50
- 424ms◆ (best)
- p99
- 5.59s
- Throughput
- 36 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.800
parasail/fp8fp8 - Novita99.40%Healthy24h 97.43%
- 7d
- 96.66%
- 30d
- 97.79%
- p50
- 723ms
- p99
- 29.5s
- Throughput
- 44 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.580
novita/fp8fp8 - Alibaba96.43%Healthy24h 98.69%
- 7d
- 97.72%
- 30d
- 99.00%
- p50
- 478ms
- p99
- 5.42s◆ (best)
- Throughput
- 58 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.150 / $0.598
alibaba - Nebius18.18%Down24h 89.82%
- 7d
- 92.20%
- 30d
- 91.46%
- p50
- 5.01s
- p99
- 45.9s
- Throughput
- 15 tps
- Context
- 262K
- $/Mtok
- $0.200 / $0.600
nebius/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 98.27%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.200 / $0.880
atlas-cloud/fp8fp8 - No data24h —
- 7d
- 95.44%
- 30d
- 95.44%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.250 / $1.00
primeintellect
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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, averaged over the hour.
Throughput
Median tokens per second.