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
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Alibabaalibaba/opensource | Healthy | 100% | 99.45% | 879ms | 2.84s | 38 tps | 262K | $0.975 / $4.88 |
DeepInfradeepinfra/turbofp4 | Healthy | 100% | 97.21% | 583ms | 4.52s | 51 tps | 262K | $0.300 / $1.00 |
Googlegoogle-vertex/us-south1 | Healthy | 100% | 99.75% | 516ms | 3.29s | 75 tps | 262K | $0.220 / $1.80 |
Venicevenice/fp8fp8 | Healthy | 100% | 83.87% | 533ms | 3.80s | 60 tps | 256K | $0.350 / $1.50 |
Novitanovita/fp8fp8 | No data | — | 89.08% | 1.01s | 6.28s | 37 tps | 262K | $0.380 / $1.55 |
- Alibaba100%Healthy24h 99.45%
- p50
- 879ms
- p99
- 2.84s
- Throughput
- 38 tps
- Context
- 262K
- $/Mtok
- $0.975 / $4.88
alibaba/opensource - DeepInfra100%Healthy24h 97.21%
- p50
- 583ms
- p99
- 4.52s
- Throughput
- 51 tps
- Context
- 262K
- $/Mtok
- $0.300 / $1.00
deepinfra/turbofp4 - Google100%Healthy24h 99.75%
- p50
- 516ms
- p99
- 3.29s
- Throughput
- 75 tps
- Context
- 262K
- $/Mtok
- $0.220 / $1.80
google-vertex/us-south1 - Venice100%Healthy24h 83.87%
- p50
- 533ms
- p99
- 3.80s
- Throughput
- 60 tps
- Context
- 256K
- $/Mtok
- $0.350 / $1.50
venice/fp8fp8 - Novita—No data24h 89.08%
- p50
- 1.01s
- p99
- 6.28s
- Throughput
- 37 tps
- Context
- 262K
- $/Mtok
- $0.380 / $1.55
novita/fp8fp8
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.