Qwen3 Coder 480B A35B

alibaba

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts). Pricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.

Try Now

Capabilities

Tool Use

Example Use Cases

Most capable open-source coding model

Agentic coding with tool use

Repository-level code reasoning

Technical Specifications

Context Window

262,144 tokens

Max Output

65,536 tokens

Cache Miss Cost

$0.22 per 1M tokens

Non-Reasoning Cost

$1 per 1M tokens

Cache Read Cost

$0.022 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