# Qwen: Qwen3 Coder 30B A3B Instruct

Provider: qwen  
Category: llm  
Model ID: `qwen/qwen3-coder-30b-a3b-instruct`

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...

## Specs

- Context length: 160000 tokens
- Max output: 32768 tokens
- Modalities: text
- Released: 2025-07-31

## Pricing

- Input: $0.07 per million tokens
- Output: $0.27 per million tokens

## Providers

- **qwen** — ctx 160000, input $0.07/M, output $0.27/M

---
Last verified: 2026-04-23T23:46:29.618Z  
Canonical URL: https://switchy.build/models/qwen3-coder-30b-a3b-instruct