Qwen3 VL 8B Instruct
qwen/qwen3-vl-8b-instruct
Compare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B
CompareQwen3 VL 8B Instruct
- Alibaba100%Healthy24h 99.98%
- 7d
- 99.98%
- 30d
- 99.98%
- p50
- 500ms
- p99
- 1.77s
- Throughput
- 30 tps
- Context
- 131K
- $/Mtok
- $0.117 / $0.455
alibaba - Parasail100%Healthy24h 99.35%
- 7d
- 98.98%
- 30d
- 98.98%
- p50
- 621ms
- p99
- 5.41s
- Throughput
- 24 tps
- Context
- 262K
- $/Mtok
- $0.250 / $0.750
parasail/bf16bf16
Measured 5m 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.