Qwen3 VL 8B Thinking
qwen/qwen3-vl-8b-thinkingInputOutput
Incident RSSCompare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 VL 235B A22B Instruct
Showing only the alibaba provider · show all 1
CompareQwen3 VL 8B Thinking
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | No data | — | 99.97% | 99.95% | 99.99% | 398ms | 882ms | 118 tps | 131K | $0.180 / $2.10 |
- No data24h 99.97%
- 7d
- 99.95%
- 30d
- 99.99%
- p50
- 398ms
- p99
- 882ms
- Throughput
- 118 tps
- Context
- 131K
- $/Mtok
- $0.180 / $2.10
alibaba
Measured 3m 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 · 1 endpoint · 42 days with data, none below the red threshold. Tables and charts above are filtered to alibaba.