Skip to content
Qwen (Alibaba)

Qwen3 Coder 480B A35B

flagship
Qwen (Alibaba) · released 2025-06-01 · text
currently routing · 4.2k rpm
131.1M tokens
Context
— / 1M
Input
— / 1M
Output
— t/s
Speed
open
License
/ ABOUT

Qwen3 Coder 480B A35B is Alibaba's specialized coding model using a Mixture-of-Experts architecture with 480 billion total parameters and 35 billion active per token. It's the largest code-focused model in the Qwen3 family, designed for complex software development tasks including multi-file codebase understanding and generation.

The model excels at code generation across dozens of programming languages, debugging complex issues, code refactoring, test generation, and explaining code logic. Its large expert capacity enables deep understanding of code patterns, architecture decisions, and best practices across diverse software domains.

Qwen3 Coder 480B is recommended for demanding coding applications including AI coding agents, automated code review, and complex software development tasks requiring frontier-level code intelligence.

Providers for Qwen3 Coder 480B A35B

4 routes · sorted by uptime

ClosedRouter routes requests to the providers best able to handle your prompt size and parameters, with automatic fallbacks to maximize uptime.

Provider
Context
Quant
Uptime · 30d
bf16
0.00%
bf16
0.00%
bf16
0.00%