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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 99.87% | 99.47% | 99.47% | 99.81% | 545ms | 2.05s | 83 tps | 131K | $0.130 / $0.520 |
| Healthy | 99.79% | 99.82% | 99.75% | 91.34% | 841ms | 4.82s | 28 tps | 262K | $0.150 / $0.600 | |
| Healthy | 98.06% | 98.73% | 98.88% | 97.55% | 971ms | 5.58s | 56 tps | 131K | $0.200 / $0.700 | |
| No data | — | — | — | — | — | — | — | 131K | $0.090 / $0.400 | |
| Down | — | 81.18% | 69.21% | 84.77% | 2.02s | 5.05s | 23 tps | 262K | $0.290 / $1.00 |
- Alibaba99.87%Healthy24h 99.47%
- 7d
- 99.47%
- 30d
- 99.81%
- p50
- 545ms
- p99
- 2.05s
- Throughput
- 83 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.520
alibaba - DeepInfra99.79%Healthy24h 99.82%
- 7d
- 99.75%
- 30d
- 91.34%
- p50
- 841ms
- p99
- 4.82s
- Throughput
- 28 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.600
deepinfra/fp8fp8 - Novita98.06%Healthy24h 98.73%
- 7d
- 98.88%
- 30d
- 97.55%
- p50
- 971ms
- p99
- 5.58s
- Throughput
- 56 tps
- Context
- 131K
- $/Mtok
- $0.200 / $0.700
novita/bf16bf16 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.090 / $0.400
darkbloom/fp4fp4 - Down24h 81.18%
- 7d
- 69.21%
- 30d
- 84.77%
- p50
- 2.02s
- p99
- 5.05s
- Throughput
- 23 tps
- Context
- 262K
- $/Mtok
- $0.290 / $1.00
siliconflow/fp8fp8
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint has no chartable data in this range.
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 · 5 endpoints · 46 days with data, 98 endpoint-days below 90%.