Qwen3 Coder 480B A35B
qwen/qwen3-coderInputOutput
Compare its 5 providersIncident RSSCompare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Next 80B A3B Instruct
CompareQwen3 Coder 480B A35B
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 98.16% | 96.09% | 96.21% | 650ms | 5.53s | 41 tps | 262K | $0.300 / $1.00 | |
Googlegoogle-vertex/us-south1 | Healthy | 100% | 99.97% | 99.80% | 99.89% | 561ms | 6.42s | 64 tps | 262K | $0.220 / $1.80 |
| Healthy | 100% | 96.79% | 90.16% | 90.12% | 828ms | 6.14s | 26 tps | 256K | $0.350 / $1.50 | |
Alibabaalibaba/opensource | No data | — | 99.92% | 99.96% | 99.75% | 772ms | 4.11s | 44 tps | 262K | $0.975 / $4.88 |
| Down | — | 74.87% | 62.28% | 84.21% | 695ms | 1.88s | 41 tps | 262K | $0.380 / $1.55 |
- DeepInfra100%Healthy24h 98.16%
- 7d
- 96.09%
- 30d
- 96.21%
- p50
- 650ms
- p99
- 5.53s
- Throughput
- 41 tps
- Context
- 262K
- $/Mtok
- $0.300 / $1.00
deepinfra/turbofp4 - Google100%Healthy24h 99.97%
- 7d
- 99.80%
- 30d
- 99.89%
- p50
- 561ms
- p99
- 6.42s
- Throughput
- 64 tps
- Context
- 262K
- $/Mtok
- $0.220 / $1.80
google-vertex/us-south1 - Venice100%Healthy24h 96.79%
- 7d
- 90.16%
- 30d
- 90.12%
- p50
- 828ms
- p99
- 6.14s
- Throughput
- 26 tps
- Context
- 256K
- $/Mtok
- $0.350 / $1.50
venice/fp8fp8 - No data24h 99.92%
- 7d
- 99.96%
- 30d
- 99.75%
- p50
- 772ms
- p99
- 4.11s
- Throughput
- 44 tps
- Context
- 262K
- $/Mtok
- $0.975 / $4.88
alibaba/opensource - Down24h 74.87%
- 7d
- 62.28%
- 30d
- 84.21%
- p50
- 695ms
- p99
- 1.88s
- Throughput
- 41 tps
- Context
- 262K
- $/Mtok
- $0.380 / $1.55
novita/fp8fp8
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 is OpenRouter's rolling 30-minute window, averaged over the hour.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 5 endpoints · 48 days with data, 129 endpoint-days below 90%.