Qwen3 30B A3B Instruct 2507
qwen/qwen3-30b-a3b-instruct-2507InputOutput
Compare its 6 providersIncident RSSCompare with Qwen3 235B A22B Instruct 2507, Qwen3 Coder 480B A35B, Qwen3 Next 80B A3B Instruct
CompareQwen3 30B A3B Instruct 2507
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.50% | 99.65% | 99.86% | 313ms | 1.20s | 72 tps | 131K | $0.130 / $0.520 |
| Healthy | 99.74% | 98.94% | 98.85% | 97.68% | 1.10s | 10.7s | 26 tps | 262K | $0.090 / $0.300 | |
StreamLakestreamlake | Healthy | 99.24% | 98.97% | 98.85% | 98.90% | 1.02s | 4.43s | 90 tps | 128K | $0.048 / $0.193 |
DekaLLMdekallm | Healthy | 99.16% | 98.89% | 98.52% | 98.89% | 421ms | 5.40s | 78 tps | 262K | $0.090 / $0.300 |
| Healthy | 98.51% | 92.90% | 94.15% | 93.85% | 438ms | 3.34s | 16 tps | 262K | $0.100 / $0.300 | |
| No data | — | — | — | 99.96% | — | — | — | 262K | $0.100 / $0.300 |
- Alibaba100%Healthy24h 99.50%
- 7d
- 99.65%
- 30d
- 99.86%
- p50
- 313ms
- p99
- 1.20s
- Throughput
- 72 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.520
alibaba - SiliconFlow99.74%Healthy24h 98.94%
- 7d
- 98.85%
- 30d
- 97.68%
- p50
- 1.10s
- p99
- 10.7s
- Throughput
- 26 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.300
siliconflow/fp8fp8 - StreamLake99.24%Healthy24h 98.97%
- 7d
- 98.85%
- 30d
- 98.90%
- p50
- 1.02s
- p99
- 4.43s
- Throughput
- 90 tps
- Context
- 128K
- $/Mtok
- $0.048 / $0.193
streamlake - DekaLLM99.16%Healthy24h 98.89%
- 7d
- 98.52%
- 30d
- 98.89%
- p50
- 421ms
- p99
- 5.40s
- Throughput
- 78 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.300
dekallm - Nebius98.51%Healthy24h 92.90%
- 7d
- 94.15%
- 30d
- 93.85%
- p50
- 438ms
- p99
- 3.34s
- Throughput
- 16 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
nebius/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 99.96%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
coreweave/bf16bf16
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 · 6 endpoints · 46 days with data, 55 endpoint-days below 90%.