Qwen3 Coder Next
Qwen3 Coder Next is an open-weight language model developed by Qwen, specifically optimized for coding agents and development workflows. It utilizes a sparse Mixture-of-Experts design to handle large-scale text inputs and outputs while supporting tool calling.
Qwen3 Coder Next specs and pricing
- Provider: Qwen
- Released: February 4, 2026
- Context window: 262K tokens
- Max output: 236K tokens
- Input: text
- Output: text
- Price: $0.12 input / $0.80 output per 1M tokens
- Tool calling: yes
What Qwen3 Coder Next is good at
- Automating software development tasks
- Integrating into local coding environments
- Processing large codebases for analysis
To-dos to try with Qwen3 Coder Next
- Analyze this repository of 50 files and suggest a refactoring plan for the authentication module.
- Write a unit test suite for the provided Python function based on the existing project structure.
- Use tool calling to fetch the latest documentation for this library and update the implementation accordingly.
FAQ
- What is Qwen3 Coder Next primarily designed for? It is designed as a causal language model specifically optimized for coding agents and local development workflows.
- Does this model support tool calling? Yes, Qwen3 Coder Next includes support for tool calling capabilities.
- How much does Qwen3 Coder Next cost? Qwen3 Coder Next costs $0.12 per million input tokens and $0.80 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.45 credits ($1 = 100 credits).
- What is the context window of Qwen3 Coder Next? Qwen3 Coder Next can read up to 262K tokens at once and write up to 236K tokens in one reply.
- Can I use Qwen3 Coder Next without coding? Yes. In todo.is you pick Qwen3 Coder Next 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.