Qwen3 14B
qwen/qwen3-14b
Compare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B
CompareQwen3 14B
- Alibaba100%Healthy24h 99.89%
- p50
- 212ms
- p99
- 676ms
- Throughput
- 63 tps
- Context
- 131K
- $/Mtok
- $0.227 / $0.910
alibaba - NextBit100%Healthy24h 99.90%
- p50
- 758ms
- p99
- 1.90s
- Throughput
- 56 tps
- Context
- 41K
- $/Mtok
- $0.100 / $0.220
nextbit/int4int4 - DeepInfra99.65%Healthy24h 95.80%
- p50
- 410ms
- p99
- 5.87s
- Throughput
- 40 tps
- Context
- 41K
- $/Mtok
- $0.120 / $0.240
deepinfra/fp8fp8
Measured 1m 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.