Alibaba
Qwen3 14B
Qwen instruction model for multilingual chat, reasoning, and tool use
Model facts
- Context window
- 131K tokens
- Maximum output
- 33K tokens
- Cheapest paid input
- $0.05 per 1M tokens
- Cheapest paid output
- $0.22 per 1M tokens
- Open weights
- yes
- Providers
- 6
Capabilities and modalities
reasoning, tool calling, structured output, temperature control, open weights, text.
Local hardware estimate
At 4K context: Q4_K_M 10.0 GiB, Q8_0 16.9 GiB, F16 29.8 GiB working memory.
- Parameters
- 14.8 billion
- Architecture
- qwen3
- Model license
- apache-2.0
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| Reasoning | 10.4 | 13.8 | 55.7 | not measured |
| Non-reasoning | 6.8 | not measured | 58.0 | not measured |
Observed price history
- 2026-08-24: $0.05 input / $0.22 output per 1M tokens
API providers
- Weights & Biases — model id OpenPipe/Qwen3-14B-Instruct; $0.05 input / $0.22 output per 1M tokens; provider documentation
- NanoGPT — model id qwen/qwen3-14b; $0.08 input / $0.24 output per 1M tokens; provider documentation
- OpenRouter — model id qwen/qwen3-14b; $0.12 input / $0.24 output per 1M tokens; provider documentation
- Vercel AI Gateway — model id alibaba/qwen-3-14b; $0.12 input / $0.24 output per 1M tokens; provider documentation
- Alibaba (China) — model id qwen3-14b; $0.144 input / $0.574 output per 1M tokens; provider documentation
- Alibaba — model id qwen3-14b; $0.35 input / $1.4 output per 1M tokens; provider documentation