Qwen3 30B A3B: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
- Alibaba100%◆ (best)Healthy24h 99.99%
- 7d
- 99.98%◆ (best)
- 30d
- 99.98%◆ (best)
- p50
- 446ms
- p99
- 4.90s
- Throughput
- 93 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.130 / $0.520
alibaba - DeepInfra100%◆ (best)Healthy24h 99.83%
- 7d
- 99.17%
- 30d
- 99.17%
- p50
- 278ms◆ (best)
- p99
- 1.58s◆ (best)
- Throughput
- 78 tps
- Context
- 41K
- $/Mtok
- $0.120 / $0.500◆ (best)
deepinfra/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.
Throughput
Median tokens per second.