← Back to Directory

Qwen: Qwen3 Coder 30B A3B Instruct

QWEN Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1431Chatbot Arena Verified
Max Context160,000Tokens
API Cost / 1M$0.34Blended Prompt + Completion

Model Capabilities

  • Coding & Logic
  • Classification
  • Fictional
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...

Granular Pricing Matrix

Input Tokens (Prompt)$0.07 / 1M
Output Tokens (Completion)$0.27 / 1M

Pricing data via OpenRouter. Sync: 4/30/2026

Evaluate Competitors

VS Engine MatchupQwen: Qwen3 Coder 30B A3B Instruct vs OpenAI GPT Mini LatestVS Engine MatchupQwen: Qwen3 Coder 30B A3B Instruct vs xAI: Grok 4.1 FastVS Engine MatchupQwen: Qwen3 Coder 30B A3B Instruct vs Qwen: Qwen3 235B A22BVS Engine MatchupQwen: Qwen3 Coder 30B A3B Instruct vs OpenAI: o3VS Engine MatchupQwen: Qwen3 Coder 30B A3B Instruct vs DeepSeek: DeepSeek V3VS Engine MatchupQwen: Qwen3 Coder 30B A3B Instruct vs OpenAI: GPT-3.5 Turbo (older v0613)