← 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) | 98.09% | 82.03% | 89.72% | 444ms | 5.84s | 24 tps | 262K | $0.090 / $0.550 | |
Googlegoogle-vertex/us-south1 | Healthy | 100%◆ (best) | 99.88% | 99.61% | 99.82% | 709ms | 29.2s | 22 tps | 262K | $0.220 / $0.880 |
| Healthy | 99.91% | 99.82% | 99.89%◆ (best) | 99.84%◆ (best) | 423ms◆ (best) | 5.98s | 36 tps | 131K | $0.140 / $0.800 | |
StreamLakestreamlake | Healthy | 99.84% | 99.31% | 98.64% | 98.81% | 591ms | 13.4s | 54 tps | 128K | $0.210 / $0.840 |
| Healthy | 99.72% | 97.44% | 96.66% | 97.79% | 725ms | 34.3s | 44 tps | 131K | $0.090 / $0.580 | |
| Healthy | 99.71% | 99.46% | 98.60% | 98.55% | 1.28s | 17.9s | 49 tps | 262K | $0.087 / $0.350◆ (best) | |
| Healthy | 99.48% | 97.45% | 90.29% | 93.77% | 618ms | 6.36s | 27 tps | 128K | $0.150 / $0.750 | |
Alibabaalibaba | Healthy | 98.79% | 98.69% | 97.72% | 99.00% | 488ms | 5.30s◆ (best) | 56 tps◆ (best) | 131K | $0.150 / $0.598 |
| Down | 17.95% | 89.76% | 92.20% | 91.46% | 5.57s | 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 |
- DeepInfra100%◆ (best)Healthy24h 98.09%
- 7d
- 82.03%
- 30d
- 89.72%
- p50
- 444ms
- p99
- 5.84s
- Throughput
- 24 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.550
deepinfra/fp8fp8 - Google100%◆ (best)Healthy24h 99.88%
- 7d
- 99.61%
- 30d
- 99.82%
- p50
- 709ms
- p99
- 29.2s
- Throughput
- 22 tps
- Context
- 262K
- $/Mtok
- $0.220 / $0.880
google-vertex/us-south1 - Parasail99.91%Healthy24h 99.82%
- 7d
- 99.89%◆ (best)
- 30d
- 99.84%◆ (best)
- p50
- 423ms◆ (best)
- p99
- 5.98s
- Throughput
- 36 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.800
parasail/fp8fp8 - StreamLake99.84%Healthy24h 99.31%
- 7d
- 98.64%
- 30d
- 98.81%
- p50
- 591ms
- p99
- 13.4s
- Throughput
- 54 tps
- Context
- 128K
- $/Mtok
- $0.210 / $0.840
streamlake - Novita99.72%Healthy24h 97.44%
- 7d
- 96.66%
- 30d
- 97.79%
- p50
- 725ms
- p99
- 34.3s
- Throughput
- 44 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.580
novita/fp8fp8 - GMICloud99.71%Healthy24h 99.46%
- 7d
- 98.60%
- 30d
- 98.55%
- p50
- 1.28s
- p99
- 17.9s
- Throughput
- 49 tps
- Context
- 262K
- $/Mtok
- $0.087 / $0.350◆ (best)
gmicloud/fp8fp8 - Venice99.48%Healthy24h 97.45%
- 7d
- 90.29%
- 30d
- 93.77%
- p50
- 618ms
- p99
- 6.36s
- Throughput
- 27 tps
- Context
- 128K
- $/Mtok
- $0.150 / $0.750
venice/fp8fp8 - Alibaba98.79%Healthy24h 98.69%
- 7d
- 97.72%
- 30d
- 99.00%
- p50
- 488ms
- p99
- 5.30s◆ (best)
- Throughput
- 56 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.150 / $0.598
alibaba - Nebius17.95%Down24h 89.76%
- 7d
- 92.20%
- 30d
- 91.46%
- p50
- 5.57s
- 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 1m 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.
Throughput
Median tokens per second.