A
Qwen3 14BOPEN
Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue.
Prices update automatically — checked daily against provider list prices.
- $0.15 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 68% of the 191 open-weight models tracked here
- 8 of 51 Alibaba models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Qwen3 14B, measured by Artificial Analysis. Higher is better. Measurement mode: Reasoning.
Models at this level cost $0.23 per 1M tokens (median of 23) — this one costs $0.15.
Cheaper and better on this index: GLM 5.3 Flash · DeepSeek V4 Flash 0731 · DeepSeek V4 Flash 0423 and 15 more
About this model
Qwen3 14B is an open-weight AI model by Alibaba. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Qwen3 14B?
Qwen3 14B is an AI language model from Alibaba. It is open-weight: you can download it and run it on your own hardware, for free. It scores 10.4 on the Artificial Analysis intelligence index.
Is Qwen3 14B free?
The weights are free and open — you can self-host Qwen3 14B and pay nothing per token. If you prefer a hosted API, list prices are $0.12 per million input tokens and $0.24 per million output tokens.
What is Qwen3 14B good at?
Independent benchmarks from Artificial Analysis give it GPQA 60.4%, MMLU-Pro 77.4%, Humanity's Last Exam 4.5%, Long Context Reasoning 0%, LiveCodeBench 52.3%, SciCode 31.6%, MATH-500 96.1%, AIME 76.3%, AIME 2025 55.7%, IFBench 40.5%, τ²-Bench 34.5%, τ-Bench Banking 5.6%, Terminal-Bench 4.9%, Terminal-Bench Hard 3.8%. It is particularly used for code generation.
Can I self-host Qwen3 14B?
Yes. Qwen3 14B has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.