Qwen3 235B A22B Thinking 2507
qwen/qwen3-235b-a22b-thinking-2507InputOutput
Compare its 4 providersIncident RSSCompare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 VL 235B A22B Instruct
Showing only the novita/fp8 provider · show all 4
CompareQwen3 235B A22B Thinking 2507
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| No data | — | 100% | 99.21% | 98.06% | 1.30s | 4.05s | 47 tps | 131K | $0.300 / $3.00 |
- No data24h 100%
- 7d
- 99.21%
- 30d
- 98.06%
- p50
- 1.30s
- p99
- 4.05s
- Throughput
- 47 tps
- Context
- 131K
- $/Mtok
- $0.300 / $3.00
novita/fp8fp8
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 4 endpoints · 47 days with data, 26 endpoint-days below 90%. Tables and charts above are filtered to novita/fp8.