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% | 99.43% | 1.30s | 23.3s | 18 tps | 262K | $0.975 / $4.88 |
DeepInfradeepinfra/turbofp4 | Healthy | 100% | 96.88% | 308ms | 22.2s | 90 tps | 262K | $0.300 / $1.00 |
Novitanovita/fp8fp8 | Degraded | 99.19% | 89.56% | 992ms | 23.5s | 23 tps | 262K | $0.380 / $1.55 |
Googlegoogle-vertex/us-south1 | No data | — | 99.76% | 422ms | 2.12s | 64 tps | 262K | $0.220 / $1.80 |
Venicevenice/fp8fp8 | No data | — | 85.53% | 37.8s | 124s | 4.0 tps | 256K | $0.350 / $1.50 |
- Alibaba100%Healthy24h 99.43%
- p50
- 1.30s
- p99
- 23.3s
- Throughput
- 18 tps
- Context
- 262K
- $/Mtok
- $0.975 / $4.88
alibaba/opensource - DeepInfra100%Healthy24h 96.88%
- p50
- 308ms
- p99
- 22.2s
- Throughput
- 90 tps
- Context
- 262K
- $/Mtok
- $0.300 / $1.00
deepinfra/turbofp4 - Novita99.19%Degraded24h 89.56%
- p50
- 992ms
- p99
- 23.5s
- Throughput
- 23 tps
- Context
- 262K
- $/Mtok
- $0.380 / $1.55
novita/fp8fp8 - Google—No data24h 99.76%
- p50
- 422ms
- p99
- 2.12s
- Throughput
- 64 tps
- Context
- 262K
- $/Mtok
- $0.220 / $1.80
google-vertex/us-south1 - Venice—No data24h 85.53%
- p50
- 37.8s
- p99
- 124s
- Throughput
- 4.0 tps
- Context
- 256K
- $/Mtok
- $0.350 / $1.50
venice/fp8fp8
Measured 3m 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.