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%
- 7d
- 99.95%
- 30d
- 99.95%
- p50
- 220ms
- p99
- 4.09s
- Throughput
- 57 tps
- Context
- 131K
- $/Mtok
- $0.227 / $0.910
alibaba - DeepInfra100%Healthy24h 95.84%
- 7d
- 96.79%
- 30d
- 96.79%
- p50
- 429ms
- p99
- 6.45s
- Throughput
- 54 tps
- Context
- 41K
- $/Mtok
- $0.120 / $0.240
deepinfra/fp8fp8 - NextBit100%Healthy24h 99.92%
- 7d
- 99.92%
- 30d
- 99.92%
- p50
- 1.11s
- p99
- 5.48s
- Throughput
- 33 tps
- Context
- 41K
- $/Mtok
- $0.100 / $0.220
nextbit/int4int4
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.
Throughput
Median tokens per second.