Qwen3 30B A3B Instruct 2507: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100%◆ (best) | 99.75% | 99.60%◆ (best) | 99.81%◆ (best) | 334ms | 966ms◆ (best) | 64 tps | 131K | $0.130 / $0.520 |
| Degraded | 99.89% | 91.98% | 94.05% | 93.85% | 306ms◆ (best) | 4.39s | 56 tps | 262K | $0.100 / $0.300 | |
StreamLakestreamlake | Healthy | 99.42% | 99.65% | 99.03% | 98.90% | 666ms | 3.38s | 95 tps◆ (best) | 128K | $0.048 / $0.193◆ (best) |
| Healthy | 99.18% | 98.41% | 98.82% | 97.80% | 997ms | 5.88s | 23 tps | 262K | $0.090 / $0.300 | |
DekaLLMdekallm | Healthy | 98.03% | 98.84% | 98.73% | 98.93% | 449ms | 4.12s | 73 tps | 262K | $0.090 / $0.300 |
| No data | — | — | — | — | — | — | — | 262K | $0.100 / $0.300 | |
PrimeIntellectprimeintellect | No data | — | — | 95.97% | 95.97% | — | — | — | 262K | $0.130 / $0.520 |
- Alibaba100%◆ (best)Healthy24h 99.75%
- 7d
- 99.60%◆ (best)
- 30d
- 99.81%◆ (best)
- p50
- 334ms
- p99
- 966ms◆ (best)
- Throughput
- 64 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.520
alibaba - Nebius99.89%Degraded24h 91.98%
- 7d
- 94.05%
- 30d
- 93.85%
- p50
- 306ms◆ (best)
- p99
- 4.39s
- Throughput
- 56 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
nebius/fp8fp8 - StreamLake99.42%Healthy24h 99.65%
- 7d
- 99.03%
- 30d
- 98.90%
- p50
- 666ms
- p99
- 3.38s
- Throughput
- 95 tps◆ (best)
- Context
- 128K
- $/Mtok
- $0.048 / $0.193◆ (best)
streamlake - SiliconFlow99.18%Healthy24h 98.41%
- 7d
- 98.82%
- 30d
- 97.80%
- p50
- 997ms
- p99
- 5.88s
- Throughput
- 23 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.300
siliconflow/fp8fp8 - DekaLLM98.03%Healthy24h 98.84%
- 7d
- 98.73%
- 30d
- 98.93%
- p50
- 449ms
- p99
- 4.12s
- Throughput
- 73 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.300
dekallm - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
coreweave/bf16bf16 - No data24h —
- 7d
- 95.97%
- 30d
- 95.97%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.130 / $0.520
primeintellect
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
History
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.