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% | 99.16% | 98.87% | 97.68% | 1.06s | 6.85s | 26 tps | 262K | $0.090 / $0.300 | |
Alibabaalibaba | Healthy | 99.64% | 98.95% | 99.61% | 99.83% | 306ms | 3.00s | 89 tps | 131K | $0.130 / $0.520 |
StreamLakestreamlake | Healthy | 99.61% | 99.06% | 98.83% | 98.89% | 973ms | 3.68s | 107 tps | 128K | $0.048 / $0.193 |
| Healthy | 99.24% | 93.70% | 94.64% | 93.89% | 428ms | 6.65s | 33 tps | 262K | $0.100 / $0.300 | |
DekaLLMdekallm | Healthy | 99.17% | 98.99% | 98.53% | 98.90% | 417ms | 3.94s | 96 tps | 262K | $0.090 / $0.300 |
PrimeIntellectprimeintellect | Healthy | 98.71% | 97.72% | 99.25% | 99.25% | 624ms | 10.9s | 34 tps | 262K | $0.130 / $0.520 |
| No data | — | — | — | 99.98% | — | — | — | 262K | $0.100 / $0.300 |
- SiliconFlow100%Healthy24h 99.16%
- 7d
- 98.87%
- 30d
- 97.68%
- p50
- 1.06s
- p99
- 6.85s
- Throughput
- 26 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.300
siliconflow/fp8fp8 - Alibaba99.64%Healthy24h 98.95%
- 7d
- 99.61%
- 30d
- 99.83%
- p50
- 306ms
- p99
- 3.00s
- Throughput
- 89 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.520
alibaba - StreamLake99.61%Healthy24h 99.06%
- 7d
- 98.83%
- 30d
- 98.89%
- p50
- 973ms
- p99
- 3.68s
- Throughput
- 107 tps
- Context
- 128K
- $/Mtok
- $0.048 / $0.193
streamlake - Nebius99.24%Healthy24h 93.70%
- 7d
- 94.64%
- 30d
- 93.89%
- p50
- 428ms
- p99
- 6.65s
- Throughput
- 33 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
nebius/fp8fp8 - DekaLLM99.17%Healthy24h 98.99%
- 7d
- 98.53%
- 30d
- 98.90%
- p50
- 417ms
- p99
- 3.94s
- Throughput
- 96 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.300
dekallm - PrimeIntellect98.71%Healthy24h 97.72%
- 7d
- 99.25%
- 30d
- 99.25%
- p50
- 624ms
- p99
- 10.9s
- Throughput
- 34 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.520
primeintellect - No data24h —
- 7d
- —
- 30d
- 99.98%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
coreweave/bf16bf16
Measured 3m 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 · 7 endpoints · 47 days with data, 54 endpoint-days below 90%.