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...
Rank
#177
Down 54% week over week
Tokens
3.7B
2026-08-14
Requests
312.8K
312,845
Tool calls
-
Input / M
$0.07
Output / M
$0.28
Cache / M
Free
Context
262K
262,144 tokens