Qwen3 Coder 480B A35B
qwen/qwen3-coder
Compare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Next 80B A3B Instruct
CompareQwen3 Coder 480B A35B
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 96.93% | 94.76% | 94.76% | 607ms | 19.1s | 64 tps | 262K | $0.300 / $1.00 | |
| Healthy | 100% | 92.82% | 85.75% | 85.75% | 1.37s | 8.98s | 38 tps | 256K | $0.350 / $1.50 | |
Alibabaalibaba/opensource | No data | — | 99.91% | 99.87% | 99.87% | 866ms | 866ms | 9.0 tps | 262K | $0.975 / $4.88 |
Googlegoogle-vertex/us-south1 | No data | — | 99.41% | 99.30% | 99.30% | 1.01s | 5.05s | 37 tps | 262K | $0.220 / $1.80 |
| No data | — | 92.70% | 91.74% | 91.74% | 1.08s | 6.73s | 43 tps | 262K | $0.380 / $1.55 |
- DeepInfra100%Healthy24h 96.93%
- 7d
- 94.76%
- 30d
- 94.76%
- p50
- 607ms
- p99
- 19.1s
- Throughput
- 64 tps
- Context
- 262K
- $/Mtok
- $0.300 / $1.00
deepinfra/turbofp4 - Venice100%Healthy24h 92.82%
- 7d
- 85.75%
- 30d
- 85.75%
- p50
- 1.37s
- p99
- 8.98s
- Throughput
- 38 tps
- Context
- 256K
- $/Mtok
- $0.350 / $1.50
venice/fp8fp8 - No data24h 99.91%
- 7d
- 99.87%
- 30d
- 99.87%
- p50
- 866ms
- p99
- 866ms
- Throughput
- 9.0 tps
- Context
- 262K
- $/Mtok
- $0.975 / $4.88
alibaba/opensource - No data24h 99.41%
- 7d
- 99.30%
- 30d
- 99.30%
- p50
- 1.01s
- p99
- 5.05s
- Throughput
- 37 tps
- Context
- 262K
- $/Mtok
- $0.220 / $1.80
google-vertex/us-south1 - No data24h 92.70%
- 7d
- 91.74%
- 30d
- 91.74%
- p50
- 1.08s
- p99
- 6.73s
- Throughput
- 43 tps
- Context
- 262K
- $/Mtok
- $0.380 / $1.55
novita/fp8fp8
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
3 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.