中EN Submit a tool

Qwen3 Coder 480B A35B

Rank #117 qwen

qwen/qwen3-coder-480b-a35b-07-25

Usage data date 2026-07-26 · updated daily

Leaderboard Back to home

Usage and specs

Daily rank#117
Daily tokens18.1B
Daily requests1M
Daily change +53.9%
Context window1M
Released

What is Qwen3 Coder 480B A35B

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.

Qwen3 Coder 480B A35B capabilities

Input: Text   Output: Text

JSON output Structured outputs Tool choice Tool use Knowledge cutoff 2025-06-30

Qwen3 Coder 480B A35B API pricing

Input · per 1M tokens$0.30
Output · per 1M tokens$1.00

List prices in USD; see each provider’s site for current terms.

Tools built on this model

通义听悟 Great for meeting-heavy teams, students, journalists, and researchers turning speech into knowledge; not for formal archival use without human proofreading.