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% | 99.69% | 1.13s | 12.0s | 48 tps | 262K | $0.975 / $4.88 |
Googlegoogle-vertex/us-south1 | Healthy | 100% | 99.73% | 440ms | 2.47s | 102 tps | 262K | $0.220 / $1.80 |
Novitanovita/fp8fp8 | Degraded | 94.37% | 88.60% | 1.32s | 4.16s | 56 tps | 262K | $0.380 / $1.55 |
Venicevenice/fp8fp8 | Down | 9.52% | 87.21% | 1.00s | 83.7s | 57 tps | 256K | $0.350 / $1.50 |
DeepInfradeepinfra/turbofp4 | Degraded | — | 97.11% | 431ms | 70.2s | 51 tps | 262K | $0.300 / $1.00 |
- Alibaba100%Healthy24h 99.69%
- p50
- 1.13s
- p99
- 12.0s
- Throughput
- 48 tps
- Context
- 262K
- $/Mtok
- $0.975 / $4.88
alibaba/opensource - Google100%Healthy24h 99.73%
- p50
- 440ms
- p99
- 2.47s
- Throughput
- 102 tps
- Context
- 262K
- $/Mtok
- $0.220 / $1.80
google-vertex/us-south1 - Novita94.37%Degraded24h 88.60%
- p50
- 1.32s
- p99
- 4.16s
- Throughput
- 56 tps
- Context
- 262K
- $/Mtok
- $0.380 / $1.55
novita/fp8fp8 - Venice9.52%Down24h 87.21%
- p50
- 1.00s
- p99
- 83.7s
- Throughput
- 57 tps
- Context
- 256K
- $/Mtok
- $0.350 / $1.50
venice/fp8fp8 - DeepInfra—Degraded24h 97.11%
- p50
- 431ms
- p99
- 70.2s
- Throughput
- 51 tps
- Context
- 262K
- $/Mtok
- $0.300 / $1.00
deepinfra/turbofp4
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.