← Qwen3 Coder 30B A3B Instruct
Qwen3 Coder 30B A3B Instruct: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 98.52% | 98.76% | 98.50% | 1.78s | 8.70s | 25 tps | 262K | $0.070 / $0.280◆ (best) | |
| Down | 84.10% | 97.39% | 98.47% | 97.56% | 997ms◆ (best) | 6.26s | 47 tps◆ (best) | 160K | $0.070 / $0.270◆ (best) | |
Alibabaalibaba | No data | — | 99.94% | 99.99%◆ (best) | 99.99%◆ (best) | 2.89s | 4.53s◆ (best) | 26 tps | 262K | $0.292 / $1.46 |
Amazon Bedrockamazon-bedrock | No data | — | — | — | — | — | — | — | 0 | $0.150 / $0.600 |
- SiliconFlow100%◆ (best)Healthy24h 98.52%
- 7d
- 98.76%
- 30d
- 98.50%
- p50
- 1.78s
- p99
- 8.70s
- Throughput
- 25 tps
- Context
- 262K
- $/Mtok
- $0.070 / $0.280◆ (best)
siliconflow/fp8fp8 - Novita84.10%Down24h 97.39%
- 7d
- 98.47%
- 30d
- 97.56%
- p50
- 997ms◆ (best)
- p99
- 6.26s
- Throughput
- 47 tps◆ (best)
- Context
- 160K
- $/Mtok
- $0.070 / $0.270◆ (best)
novita/fp8fp8 - No data24h 99.94%
- 7d
- 99.99%◆ (best)
- 30d
- 99.99%◆ (best)
- p50
- 2.89s
- p99
- 4.53s◆ (best)
- Throughput
- 26 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
Measured 3m 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.
Throughput
Median tokens per second.