← Back to Directory

Qwen: Qwen3 Coder 480B A35B

QWEN Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1421Chatbot Arena Verified
Max Context262,144Tokens
API Cost / 1M$2.02Blended Prompt + Completion

Model Capabilities

  • Coding & Logic
  • Fictional
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...

Granular Pricing Matrix

Input Tokens (Prompt)$0.22 / 1M
Output Tokens (Completion)$1.80 / 1M

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

Evaluate Competitors

VS Engine MatchupQwen: Qwen3 Coder 480B A35B vs Qwen: Qwen3 Coder PlusVS Engine MatchupQwen: Qwen3 Coder 480B A35B vs Mistral: Devstral MediumVS Engine MatchupQwen: Qwen3 Coder 480B A35B vs Anthropic: Claude 3.5 HaikuVS Engine MatchupQwen: Qwen3 Coder 480B A35B vs Meta: Llama 3.2 3B Instruct (free)VS Engine MatchupQwen: Qwen3 Coder 480B A35B vs MythoMax 13BVS Engine MatchupQwen: Qwen3 Coder 480B A35B vs Z.ai: GLM 5.1