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...
Related Models
Pricing
Input
$0.10
per 1M tokens
Output
$0.24
per 1M tokens
Blended
$0.14
per 1M tokens
Cheaper than 80% of models. Median price is $0.67/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.14
Monthly
$4.05
vs. Similar Models
QwQ 32B-Preview
$0.140%
OpenAI: GPT-5 Nano
$0.14+2%
GPT-5 nano (medium)
$0.14+2%
GPT-5 nano (minimal)
$0.14+2%
Performance
Context Window
132K
tokens
Larger than 46% of models
Max Output
41K
tokens
31% of context
Context Window Comparison
DeepSeek: DeepSeek V3.2
131K1.0x smaller
OpenAI: gpt-oss-120b
131K1.0x smaller
MoonshotAI: Kimi K2 0711
131K1.0x smaller
Open Source
apache-2.014BGGUF / GPTQ / AWQ
Downloads
4.6M
Likes
418
VRAM (FP16)
16-24 GB
GPU
RTX 4090 / M2 Max