Qwen3 14B: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.41% | 97.29% | 98.49% | 2.40s | 16.6s | 18 tps | 41K | $0.120 / $0.240 | |
| Healthy | 100%◆ (best) | 99.98% | 99.78%◆ (best) | 99.57% | 2.71s | 9.24s | 30 tps | 41K | $0.100 / $0.220◆ (best) | |
Alibabaalibaba | No data | — | 99.95% | 99.51% | 99.80%◆ (best) | 192ms◆ (best) | 7.64s◆ (best) | 63 tps◆ (best) | 131K | $0.227 / $0.910 |
- DeepInfra100%◆ (best)Healthy24h 99.41%
- 7d
- 97.29%
- 30d
- 98.49%
- p50
- 2.40s
- p99
- 16.6s
- Throughput
- 18 tps
- Context
- 41K
- $/Mtok
- $0.120 / $0.240
deepinfra/fp8fp8 - NextBit100%◆ (best)Healthy24h 99.98%
- 7d
- 99.78%◆ (best)
- 30d
- 99.57%
- p50
- 2.71s
- p99
- 9.24s
- Throughput
- 30 tps
- Context
- 41K
- $/Mtok
- $0.100 / $0.220◆ (best)
nextbit/int4int4 - No data24h 99.95%
- 7d
- 99.51%
- 30d
- 99.80%◆ (best)
- p50
- 192ms◆ (best)
- p99
- 7.64s◆ (best)
- Throughput
- 63 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.227 / $0.910
alibaba
Measured 5m 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.