Qwen3 Coder 30B A3B Instruct
qwen/qwen3-coder-30b-a3b-instruct
Compare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B
CompareQwen3 Coder 30B A3B Instruct
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 97.96% | 95.48% | 97.53% | 97.53% | 2.19s | 29.2s | 23 tps | 262K | $0.070 / $0.280 | |
Alibabaalibaba | No data | — | 99.92% | 99.97% | 99.97% | 1.05s | 19.5s | 43 tps | 262K | $0.292 / $1.46 |
Amazon Bedrockamazon-bedrock | No data | — | — | — | — | — | — | — | 0 | $0.150 / $0.600 |
| Degraded | — | 90.69% | 92.89% | 92.89% | 1.16s | 4.98s | 36 tps | 160K | $0.070 / $0.270 |
- SiliconFlow97.96%Healthy24h 95.48%
- 7d
- 97.53%
- 30d
- 97.53%
- p50
- 2.19s
- p99
- 29.2s
- Throughput
- 23 tps
- Context
- 262K
- $/Mtok
- $0.070 / $0.280
siliconflow/fp8fp8 - No data24h 99.92%
- 7d
- 99.97%
- 30d
- 99.97%
- p50
- 1.05s
- p99
- 19.5s
- Throughput
- 43 tps
- Context
- 262K
- $/Mtok
- $0.292 / $1.46
alibaba - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 0
- $/Mtok
- $0.150 / $0.600
amazon-bedrock - Degraded24h 90.69%
- 7d
- 92.89%
- 30d
- 92.89%
- p50
- 1.16s
- p99
- 4.98s
- Throughput
- 36 tps
- Context
- 160K
- $/Mtok
- $0.070 / $0.270
novita/fp8fp8
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
2 endpoints reporting no data are omitted from the charts.
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.