← 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | No data | — | — | 97.72% | 99.00% | — | — | — | 131K | $0.150 / $0.598 |
| No data | — | — | — | 98.27% | — | — | — | 131K | $0.200 / $0.880 | |
| No data | — | — | 82.03% | 89.72% | — | — | — | 262K | $0.090 / $0.550 | |
| No data | — | — | 98.60% | 98.55% | — | — | — | 262K | $0.087 / $0.350◆ (best) | |
Googlegoogle-vertex/us-south1 | No data | — | — | 99.61% | 99.82% | — | — | — | 262K | $0.220 / $0.880 |
| No data | — | — | 92.20% | 91.46% | — | — | — | 262K | $0.200 / $0.600 | |
| No data | — | — | 96.66% | 97.79% | — | — | — | 131K | $0.090 / $0.580 | |
| No data | — | — | 99.89%◆ (best) | 99.84%◆ (best) | — | — | — | 131K | $0.140 / $0.800 | |
PrimeIntellectprimeintellect | No data | — | — | 95.44% | 95.44% | — | — | — | 262K | $0.250 / $1.00 |
StreamLakestreamlake | No data | — | — | 98.64% | 98.81% | — | — | — | 128K | $0.210 / $0.840 |
| No data | — | — | 90.29% | 93.77% | — | — | — | 128K | $0.150 / $0.750 |
- No data24h —
- 7d
- 97.72%
- 30d
- 99.00%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.150 / $0.598
alibaba - No data24h —
- 7d
- —
- 30d
- 98.27%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.200 / $0.880
atlas-cloud/fp8fp8 - No data24h —
- 7d
- 82.03%
- 30d
- 89.72%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.090 / $0.550
deepinfra/fp8fp8 - No data24h —
- 7d
- 98.60%
- 30d
- 98.55%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.087 / $0.350◆ (best)
gmicloud/fp8fp8 - No data24h —
- 7d
- 99.61%
- 30d
- 99.82%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.220 / $0.880
google-vertex/us-south1 - No data24h —
- 7d
- 92.20%
- 30d
- 91.46%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.200 / $0.600
nebius/fp8fp8 - No data24h —
- 7d
- 96.66%
- 30d
- 97.79%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.090 / $0.580
novita/fp8fp8 - No data24h —
- 7d
- 99.89%◆ (best)
- 30d
- 99.84%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.140 / $0.800
parasail/fp8fp8 - No data24h —
- 7d
- 95.44%
- 30d
- 95.44%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.250 / $1.00
primeintellect - No data24h —
- 7d
- 98.64%
- 30d
- 98.81%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 128K
- $/Mtok
- $0.210 / $0.840
streamlake - No data24h —
- 7d
- 90.29%
- 30d
- 93.77%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 128K
- $/Mtok
- $0.150 / $0.750
venice/fp8fp8
No recent measurement. ◆ marks the best value in each column among these endpoints.
Price vs latency
No endpoint currently reports both a price and a latency.
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.