Qwen3 30B A3B Instruct 2507
qwen/qwen3-30b-a3b-instruct-2507InputOutput
Compare its 7 providersIncident RSSCompare with Qwen3 235B A22B Instruct 2507, Qwen3 VL 235B A22B Instruct, Qwen3 Coder 480B A35B
CompareQwen3 30B A3B Instruct 2507
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 93.05% | 94.59% | 93.88% | 296ms | 1.62s | 83 tps | 262K | $0.100 / $0.300 | |
PrimeIntellectprimeintellect | Healthy | 100% | 91.75% | — | — | 536ms | 2.08s | 77 tps | 262K | $0.130 / $0.520 |
| Healthy | 100% | 99.12% | 98.86% | 97.68% | 908ms | 4.62s | 31 tps | 262K | $0.090 / $0.300 | |
Alibabaalibaba | Healthy | 99.41% | 99.24% | 99.66% | 99.85% | 311ms | 2.84s | 82 tps | 131K | $0.130 / $0.520 |
StreamLakestreamlake | Healthy | 99.22% | 99.04% | 98.84% | 98.90% | 888ms | 4.01s | 99 tps | 128K | $0.048 / $0.193 |
DekaLLMdekallm | Healthy | 97.50% | 98.96% | 98.53% | 98.90% | 367ms | 4.05s | 89 tps | 262K | $0.090 / $0.300 |
| No data | — | — | — | 99.97% | — | — | — | 262K | $0.100 / $0.300 |
- Nebius100%Healthy24h 93.05%
- 7d
- 94.59%
- 30d
- 93.88%
- p50
- 296ms
- p99
- 1.62s
- Throughput
- 83 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
nebius/fp8fp8 - PrimeIntellect100%Healthy24h 91.75%
- 7d
- —
- 30d
- —
- p50
- 536ms
- p99
- 2.08s
- Throughput
- 77 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.520
primeintellect - SiliconFlow100%Healthy24h 99.12%
- 7d
- 98.86%
- 30d
- 97.68%
- p50
- 908ms
- p99
- 4.62s
- Throughput
- 31 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.300
siliconflow/fp8fp8 - Alibaba99.41%Healthy24h 99.24%
- 7d
- 99.66%
- 30d
- 99.85%
- p50
- 311ms
- p99
- 2.84s
- Throughput
- 82 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.520
alibaba - StreamLake99.22%Healthy24h 99.04%
- 7d
- 98.84%
- 30d
- 98.90%
- p50
- 888ms
- p99
- 4.01s
- Throughput
- 99 tps
- Context
- 128K
- $/Mtok
- $0.048 / $0.193
streamlake - DekaLLM97.50%Healthy24h 98.96%
- 7d
- 98.53%
- 30d
- 98.90%
- p50
- 367ms
- p99
- 4.05s
- Throughput
- 89 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.300
dekallm - No data24h —
- 7d
- —
- 30d
- 99.97%
- 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, 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 · 7 endpoints · 47 days with data, 54 endpoint-days below 90%.