Qwen: Qwen3 Coder 30B A3B Instruct
160k context
Lowest Price
$0.07
per 1M tokens
Providers
1
Available
Context
160k
tokens
Price Comparison
| Provider | Input / Output | Latency | Status | |
|---|---|---|---|---|
| OpenRouterLowest | $0.07/$0.27 | ... | Verified |
About This Model
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 Qwen3 architecture, it supports a native context length of 256K tok...
Quick Start