Qwen logo

Qwen3 Coder 480B A35B (free)

480B

by Qwen

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.

Pricing

Input Tokens
Per 1M tokens
Free
Output Tokens
Per 1M tokens
Free
Image Processing
Per 1M tokens
$0.00/1M tokens

Supported Modalities

Input

text

Output

text

Specifications

Context Length
262K tokens
Provider
Qwen
Released
Jul 23, 2025
Model ID
qwen/qwen3-coder

Ready to try it?

Start chatting with Qwen3 Coder 480B A35B (free) right now. No credit card required.

Start Chatting

More from Qwen

View all models