All Models

Qwen/Qwen3-Coder-30B-A3B-Instruct

qwen Tool Calling Open Weights Structured Output

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...

Providers 3
Released Jul 31, 2025
Input Modalities text
Output Modalities text
Tarsk Use coding

Benchmarks

20
Intelligence Index
19.4
Coding Index
29
Math Index

Available Providers (3)

Provider Model ID Input Cost Output Cost Context Max Output Docs
SiliconFlow (China) Qwen/Qwen3-Coder-30B-A3B-Instruct $0.07/MTok $0.28/MTok 262K 262K
Kilo Gateway qwen/qwen3-coder-30b-a3b-instruct $0.07/MTok $0.27/MTok 160K 32.8K
SiliconFlow Qwen/Qwen3-Coder-30B-A3B-Instruct $0.07/MTok $0.28/MTok 262K 262K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output