← Back to Directory

Qwen: Qwen Plus 0728 (thinking)

QWEN Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1429Chatbot Arena Verified
Max Context1,000,000Tokens
API Cost / 1M$1.04Blended Prompt + Completion

Model Capabilities

  • Coding & Logic
  • Fictional
Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.

Granular Pricing Matrix

Input Tokens (Prompt)$0.26 / 1M
Output Tokens (Completion)$0.78 / 1M

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

Evaluate Competitors

VS Engine MatchupQwen: Qwen Plus 0728 (thinking) vs Qwen: Qwen3.5-FlashVS Engine MatchupQwen: Qwen Plus 0728 (thinking) vs Z.ai: GLM 4.6VVS Engine MatchupQwen: Qwen Plus 0728 (thinking) vs Mistral: Ministral 3 8B 2512VS Engine MatchupQwen: Qwen Plus 0728 (thinking) vs Prime Intellect: INTELLECT-3VS Engine MatchupQwen: Qwen Plus 0728 (thinking) vs xAI: Grok Code Fast 1VS Engine MatchupQwen: Qwen Plus 0728 (thinking) vs Z.ai: GLM 4.5V