Qwen3 14B
Qwen3 14B is a 14.8 billion parameter language model developed by Qwen. It is designed for complex reasoning tasks and efficient dialogue, featuring a specialized mode for thinking and support for tool calling.
Qwen3 14B specs and pricing
- Provider: Qwen
- Released: April 28, 2025
- Context window: 41K tokens
- Max output: 16K tokens
- Input: text
- Output: text
- Price: $0.12 input / $0.24 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Qwen3 14B is good at
- Complex reasoning tasks
- Interactive dialogue applications
- Tasks requiring external tool integration
To-dos to try with Qwen3 14B
- Use the reasoning mode to solve a multi-step logic puzzle.
- Integrate the model into a workflow that requires calling external software tools.
- Draft a structured response for a technical conversation using the model's dialogue capabilities.
FAQ
- Who developed Qwen3 14B? Qwen3 14B is a dense causal language model created by Qwen.
- What are the primary capabilities of this model? The model is built for complex reasoning and efficient dialogue, and it supports both tool calling and a dedicated thinking mode.
- How much does Qwen3 14B cost? Qwen3 14B costs $0.12 per million input tokens and $0.24 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.37 credits ($1 = 100 credits).
- What is the context window of Qwen3 14B? Qwen3 14B can read up to 41K tokens at once and write up to 16K tokens in one reply.
- Can I use Qwen3 14B without coding? Yes. In todo.is you pick Qwen3 14B as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.