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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.10% | 99.61% | 99.83% | 305ms | 883ms | 86 tps | 131K | $0.130 / $0.520 |
DekaLLMdekallm | Healthy | 100% | 99.07% | 98.53% | 98.91% | 398ms | 3.46s | 84 tps | 262K | $0.090 / $0.300 |
| Healthy | 100% | 95.58% | 94.63% | 93.89% | 283ms | 2.86s | 92 tps | 262K | $0.100 / $0.300 | |
PrimeIntellectprimeintellect | Healthy | 100% | 98.53% | 98.75% | 98.75% | 532ms | 3.06s | 72 tps | 262K | $0.130 / $0.520 |
| Healthy | 100% | 99.02% | 98.86% | 97.68% | 1.05s | 6.87s | 30 tps | 262K | $0.090 / $0.300 | |
StreamLakestreamlake | Healthy | 97.30% | 99.05% | 98.82% | 98.89% | 800ms | 4.63s | 97 tps | 128K | $0.048 / $0.193 |
| No data | — | — | — | 99.98% | — | — | — | 262K | $0.100 / $0.300 |
- Alibaba100%Healthy24h 99.10%
- 7d
- 99.61%
- 30d
- 99.83%
- p50
- 305ms
- p99
- 883ms
- Throughput
- 86 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.520
alibaba - DekaLLM100%Healthy24h 99.07%
- 7d
- 98.53%
- 30d
- 98.91%
- p50
- 398ms
- p99
- 3.46s
- Throughput
- 84 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.300
dekallm - Nebius100%Healthy24h 95.58%
- 7d
- 94.63%
- 30d
- 93.89%
- p50
- 283ms
- p99
- 2.86s
- Throughput
- 92 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
nebius/fp8fp8 - PrimeIntellect100%Healthy24h 98.53%
- 7d
- 98.75%
- 30d
- 98.75%
- p50
- 532ms
- p99
- 3.06s
- Throughput
- 72 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.520
primeintellect - SiliconFlow100%Healthy24h 99.02%
- 7d
- 98.86%
- 30d
- 97.68%
- p50
- 1.05s
- p99
- 6.87s
- Throughput
- 30 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.300
siliconflow/fp8fp8 - StreamLake97.30%Healthy24h 99.05%
- 7d
- 98.82%
- 30d
- 98.89%
- p50
- 800ms
- p99
- 4.63s
- Throughput
- 97 tps
- Context
- 128K
- $/Mtok
- $0.048 / $0.193
streamlake - No data24h —
- 7d
- —
- 30d
- 99.98%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
coreweave/bf16bf16
Measured 2m 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%.