Qwen: Qwen3 Coder 480B A35B

Qwen3-Coder-480B-A35B-Instruct is a cutting-edge Mixture-of-Experts (MoE) code generation model developed by the Qwen team. This powerful AI is specifically optimized for complex agentic coding tasks, including efficient function calling, versatile tool use, and sophisticated long-context reasoning across extensive code repositories. With 480 billion total parameters and 35 billion active per forward pass (utilizing 8 out of 160 experts), it delivers exceptional performance for developers and AI agents. This model offers robust capabilities for functions, code generation, and streaming outputs, making it ideal for chat, advanced coding projects, and mathematical problem-solving. It boasts an impressive context window of 262K tokens and a maximum output of 4K tokens. Pricing for Alibaba endpoints varies by context length, with higher rates applied for requests exceeding 128K input tokens. The base pricing is $0.22 per 1M input tokens and $0.95 per 1M output tokens, making it a STARTER access tier model on Multi AI.