Qwen3 Coder Next

alibaba

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.

Try Now

Capabilities

Tool Use

Example Use Cases

Lightweight coding agent for local workflows

Cost-effective agentic coding

Long-horizon coding task on a budget

Technical Specifications

Context Window

262,144 tokens

Max Output

65,536 tokens

Cache Miss Cost

$0.12 per 1M tokens

Non-Reasoning Cost

$0.75 per 1M tokens

Cache Read Cost

$0.06 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Untested

Recommended Replacement

Qwen3.5 Plus