Models / Qwen
Qwen3 Coder 30B A3B Instruct
by Qwen ·
qwen/qwen3-coder-30b-a3b-instructQwen3-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...
tool-usereleased 2025-07-31
Legal score · raw
-
not yet benchmarked
Context
262K
max output 236K
Input
$0.09
per 1M tokens
Output
$0.35
per 1M tokens
Suite cost
-
no run recorded
Benchmark results
This model has not been run through the suite yet. See Humanity's Last Lawsuit for the benchmark models are ranked on.