Qwen3 VL 8B Instruct: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
- Alibaba99.58%◆ (best)Healthy24h 99.15%
- 7d
- 99.17%◆ (best)
- 30d
- 99.74%◆ (best)
- p50
- 536ms◆ (best)
- p99
- 2.61s◆ (best)
- Throughput
- 78 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.117 / $0.455◆ (best)
alibaba - Parasail98.76%Healthy24h 98.43%
- 7d
- 97.81%
- 30d
- 98.59%
- p50
- 1.39s
- p99
- 6.83s
- Throughput
- 20 tps
- Context
- 262K
- $/Mtok
- $0.250 / $0.750
parasail/bf16bf16
Measured 1m 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.