Qwen3 14B
Qwen · Open weights · Released Apr 28, 2025 · qwen/qwen3-14b
Best $0.10 in / $0.22 out via NextBit · int4
41K contextToolsReasoningStructured outputOpen weights
Available from 4 providersUSD / MTOK · PRICES 16 MINUTES AGO · SPEED 2 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.096 | $0.192 | — | 41K | fp8 | — | — | — | |
| $0.10 | $0.22 | — | 41K | int4 | 5.3s | 57 tok/s | 100.0% | |
| $0.12 | $0.24 | — | 41K | fp8 | 1.6s | 46 tok/s | 99.5% | |
| $0.18 | $0.36 | — | 41K | fp8 | — | — | 90.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 2 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Recent changesRSS ↗
Oct 29, 2026endpoint removed · cheaperinference3 → 2
Oct 23, 2026endpoint added · cheaperinference2 → 3
Oct 10, 2026endpoint removed · alibaba3 → 2
Oct 10, 2026context changed131072 → 40960
About
Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...
Specifications
Context window40,960
Max output16,384
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedApr 28, 2025
Knowledge cutoff2025-03-31
TokenizerQwen3
WeightsHugging Face ↗
Related
Embed badge
[](https://modelindex.ai/models/qwen/qwen3-14b)Sources
OpenRouter API16 minutes ago
AGGREGATORHugging Face16 minutes ago
COMMUNITYModelIndex benchmarks14 days ago
MEASUREDVerified 16 minutes ago · list prices, not negotiated rates.