Qwen3 VL 30B A3B Thinking: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | No data | — | 100% | 99.97% | 99.99%◆ (best) | 429ms◆ (best) | 1.26s◆ (best) | 114 tps◆ (best) | 131K | $0.200 / $2.40◆ (best) |
| No data | — | 99.62% | 100%◆ (best) | 99.87% | 1.14s | 3.50s | 75 tps | 262K | $0.290 / $1.00 |
- No data24h 100%
- 7d
- 99.97%
- 30d
- 99.99%◆ (best)
- p50
- 429ms◆ (best)
- p99
- 1.26s◆ (best)
- Throughput
- 114 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.200 / $2.40◆ (best)
alibaba - No data24h 99.62%
- 7d
- 100%◆ (best)
- 30d
- 99.87%
- p50
- 1.14s
- p99
- 3.50s
- Throughput
- 75 tps
- Context
- 262K
- $/Mtok
- $0.290 / $1.00
siliconflow/fp8fp8
Measured 3m 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, averaged over the hour.
Throughput
Median tokens per second.