ModelWatch
← Catalog

Qwen3 Coder 30B A3B Instruct

Alibaba (Qwen)qwenlm.github.io

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...

open-weightslow-cost
Input price
$0.07 / 1M tokens
Output price
$0.28 / 1M tokens
Context window
262K tokens
Max output
236K tokens
Output speed
126 tokens/s
Time to first token
1.62s
Inputs
text
Open weights
Yes
OpenRouter id
qwen/qwen3-coder-30b-a3b-instruct
Listed
Jul 31, 2025

Benchmarks

Intelligence Index
n/a
Engineering Index
n/a

Speed and benchmarks for “Qwen3 Coder 30B A3B Instruct” from Artificial Analysis. Prices, context window and listing date are live from OpenRouter.

Compare with others