Qwen3 Coder 480B A35B: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba/opensource | No data | — | 99.99% | 99.96%◆ (best) | 99.75% | 1.96s | 3.59s | 63 tps | 262K | $0.975 / $4.88 |
| Degraded | — | 98.57% | 96.17% | 96.05% | 1.60s | 30.7s | 40 tps | 262K | $0.300 / $1.00 | |
Googlegoogle-vertex/us-south1 | No data | — | 99.96% | 99.85% | 99.90%◆ (best) | 931ms◆ (best) | 6.74s | 90 tps◆ (best) | 262K | $0.220 / $1.80◆ (best) |
| No data | — | 94.57% | 64.57% | 84.94% | 941ms | 2.42s◆ (best) | 48 tps | 262K | $0.380 / $1.55 | |
| Degraded | — | 96.98% | 90.23% | 89.49% | 976ms | 25.2s | 36 tps | 256K | $0.350 / $1.50 |
- No data24h 99.99%
- 7d
- 99.96%◆ (best)
- 30d
- 99.75%
- p50
- 1.96s
- p99
- 3.59s
- Throughput
- 63 tps
- Context
- 262K
- $/Mtok
- $0.975 / $4.88
alibaba/opensource - Degraded24h 98.57%
- 7d
- 96.17%
- 30d
- 96.05%
- p50
- 1.60s
- p99
- 30.7s
- Throughput
- 40 tps
- Context
- 262K
- $/Mtok
- $0.300 / $1.00
deepinfra/turbofp4 - No data24h 99.96%
- 7d
- 99.85%
- 30d
- 99.90%◆ (best)
- p50
- 931ms◆ (best)
- p99
- 6.74s
- Throughput
- 90 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.220 / $1.80◆ (best)
google-vertex/us-south1 - No data24h 94.57%
- 7d
- 64.57%
- 30d
- 84.94%
- p50
- 941ms
- p99
- 2.42s◆ (best)
- Throughput
- 48 tps
- Context
- 262K
- $/Mtok
- $0.380 / $1.55
novita/fp8fp8 - Degraded24h 96.98%
- 7d
- 90.23%
- 30d
- 89.49%
- p50
- 976ms
- p99
- 25.2s
- Throughput
- 36 tps
- Context
- 256K
- $/Mtok
- $0.350 / $1.50
venice/fp8fp8
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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.