Qwen3 Coder Next
by Qwen
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per token, delivering performance comparable to models with 10 to 20x higher active compute, which makes it well suited for cost-sensitive, always-on agent deployment. The model is trained with a strong agentic focus and performs reliably on long-horizon coding tasks, complex tool usage, and recovery from execution failures. With a native 256k context window, it integrates cleanly into real-world CLI and IDE environments and adapts well to common agent scaffolds used by modern coding tools. The model operates exclusively in non-thinking mode and does not emit <think> blocks, simplifying integration for production coding agents.
Specifications
Technical details and pricing.
Benchmarks
7 benchmark scores from Artificial Analysis.
Composite Indices
Intelligence, Coding, Math
Standard Benchmarks
Academic and industry benchmarks
Frequently Asked Questions
What is Qwen3 Coder Next good for?
Use Qwen3 Coder Next for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.
How much does Qwen3 Coder Next cost?
Pricing is based on usage. Current rates are $0.20/1M tokens for input and $1.20/1M tokens for output.
Can I try Qwen3 Coder Next for free?
Yes. You can start a chat instantly and test the model before deciding on a plan.
Does Qwen3 Coder Next support images or audio?
Qwen3 Coder Next focuses on text-based tasks.
Similar Models
Other models you might want to explore.
Benchmarks and pricing are sourced from Artificial Analysis where available. OpenRouter specs are used as a fallback.