Qwen3 Coder 30B A3B Instruct

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...

262K context·$0.07 in·$0.28 out·Jul 2025 release·Tools / functions, Web search

Available on

OpenRouter AWS Bedrock Together AI

Providers

Where Qwen3 Coder 30B A3B Instruct runs in Big-AGI, with each service's own model ID and USD-per-1M-token rates. The summary above prefers the creator's claim; rates below are each service's own.

ServiceModel IDContextInputOutput

OpenRouter

qwen/qwen3-coder-30b-a3b-instruct

262K

$0.07

$0.28

AWS Bedrock

qwen.qwen3-coder-30b-a3b-instruct

131K

Together AI

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

262K