← 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
- No data24h —
- 7d
- 99.72%
- 30d
- 99.77%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.230 / $2.30◆ (best)
alibaba - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.230 / $2.30◆ (best)
deepinfra/fp8fp8 - No data24h —
- 7d
- 99.90%◆ (best)
- 30d
- 99.04%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.300 / $3.00
novita/fp8fp8 - No data24h 93.24%
- 7d
- 99.82%
- 30d
- 98.62%
- p50
- 42.6s
- p99
- 332s
- Throughput
- 6.0 tps
- Context
- 128K
- $/Mtok
- $0.450 / $3.50
venice/fp8fp8
Measured 2m 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.