Qwen3 VL 30B A3B Instruct
qwen/qwen3-vl-30b-a3b-instructInputOutput
Compare its 5 providersIncident RSSCompare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B
CompareQwen3 VL 30B A3B Instruct
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.83% | 99.75% | 91.34% | 1.23s | 6.74s | 19 tps | 262K | $0.150 / $0.600 | |
| Healthy | 97.79% | 98.72% | 98.87% | 97.57% | 837ms | 6.00s | 85 tps | 131K | $0.200 / $0.700 | |
Alibabaalibaba | Healthy | 97.75% | 99.44% | 99.46% | 99.80% | 361ms | 3.03s | 60 tps | 131K | $0.130 / $0.520 |
| No data | — | — | — | — | — | — | — | 131K | $0.090 / $0.400 | |
| Down | — | 81.25% | 69.11% | 84.74% | 2.45s | 73.9s | 26 tps | 262K | $0.290 / $1.00 |
- DeepInfra100%Healthy24h 99.83%
- 7d
- 99.75%
- 30d
- 91.34%
- p50
- 1.23s
- p99
- 6.74s
- Throughput
- 19 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.600
deepinfra/fp8fp8 - Novita97.79%Healthy24h 98.72%
- 7d
- 98.87%
- 30d
- 97.57%
- p50
- 837ms
- p99
- 6.00s
- Throughput
- 85 tps
- Context
- 131K
- $/Mtok
- $0.200 / $0.700
novita/bf16bf16 - Alibaba97.75%Healthy24h 99.44%
- 7d
- 99.46%
- 30d
- 99.80%
- p50
- 361ms
- p99
- 3.03s
- Throughput
- 60 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.520
alibaba - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.090 / $0.400
darkbloom/fp4fp4 - Down24h 81.25%
- 7d
- 69.11%
- 30d
- 84.74%
- p50
- 2.45s
- p99
- 73.9s
- Throughput
- 26 tps
- Context
- 262K
- $/Mtok
- $0.290 / $1.00
siliconflow/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, averaged over the hour.
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 · 5 endpoints · 46 days with data, 98 endpoint-days below 90%.