← Qwen3 235B A22B Thinking 2507
Qwen3 235B A22B Thinking 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% | 99.98% | 99.09% | 99.09% | 645ms◆ (best) | 12.4s | 41 tps | 262K | $0.230 / $2.30◆ (best) | |
Alibabaalibaba | No data | — | 99.96% | 99.83% | 99.83% | 938ms | 9.46s◆ (best) | 65 tps◆ (best) | 131K | $0.230 / $2.30◆ (best) |
| No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 2.46s | 16.7s | 26 tps | 131K | $0.300 / $3.00 | |
| No data | — | 99.20% | 100%◆ (best) | 100%◆ (best) | 993ms | 15.1s | 42 tps | 128K | $0.450 / $3.50 |
- DeepInfra100%Healthy24h 99.98%
- 7d
- 99.09%
- 30d
- 99.09%
- p50
- 645ms◆ (best)
- p99
- 12.4s
- Throughput
- 41 tps
- Context
- 262K
- $/Mtok
- $0.230 / $2.30◆ (best)
deepinfra/fp8fp8 - No data24h 99.96%
- 7d
- 99.83%
- 30d
- 99.83%
- p50
- 938ms
- p99
- 9.46s◆ (best)
- Throughput
- 65 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.230 / $2.30◆ (best)
alibaba - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 2.46s
- p99
- 16.7s
- Throughput
- 26 tps
- Context
- 131K
- $/Mtok
- $0.300 / $3.00
novita/fp8fp8 - No data24h 99.20%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 993ms
- p99
- 15.1s
- Throughput
- 42 tps
- Context
- 128K
- $/Mtok
- $0.450 / $3.50
venice/fp8fp8
Measured 5m 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.