Qwen3 Next 80B Thinking

alibaba

A next-generation thinking model that balances power with efficiency through innovative architecture. This model shines when you need deep reasoning without the cost of larger models. With 164K context and explicit thinking capabilities, it works through complex problems step-by-step, making it ideal for analytical tasks, research, and situations where you want to see the reasoning process. Extremely cost-effective for thoughtful, deliberate problem-solving.

Try Now

Capabilities

Tool Use

Extended Thinking

Example Use Cases

Need step-by-step reasoning explanation

Analytical task on a budget

Want to see the thought process

Technical Specifications

Context Window

65,536 tokens

Max Output

65,536 tokens

Cache Miss Cost

$0.15 per 1M tokens

Non-Reasoning Cost

$1.50 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls