Skip to main content
Alibaba Cloud’s Qwen (通义千问) is a comprehensive family of AI models offering everything from compact 0.6B parameter models to massive 235B MoE models. Qwen3 series features hybrid thinking capabilities and strong coding performance. Website: https://bailian.console.aliyun.com/

​
Getting an API Key

  1. Sign Up/Sign In: Go to the Alibaba Cloud Bailian Console. Create an account or sign in.
  2. Navigate to API Keys: Access the API key management section.
  3. Create a Key: Generate a new API key for your application.
  4. Copy the Key: Copy the API key immediately and store it securely.

​
Supported Models

Cline supports Qwen models with separate catalogs for International and China regions:

​
Qwen3 Coder Series

  • qwen3-coder-plus - High-performance coding model with 1M context (1.00/1.00/5.00 per 1M tokens)
  • qwen3-coder-480b-a35b-instruct - 480B MoE coding model with 204K context (1.50/1.50/7.50 per 1M tokens)

​
Qwen3 Thinking Models

  • qwen3-235b-a22b - 235B MoE model with thinking support (131K context, 2.00/2.00/8.00 per 1M tokens)
  • qwen3-32b - Dense 32B model with thinking (131K context)
  • qwen3-30b-a3b - Compact 30B MoE with thinking (131K context)
  • qwen3-14b - Mid-size model with thinking (131K context)
  • qwen3-8b - Efficient model with thinking (131K context)
  • qwen3-4b - Compact model with thinking (131K context)
  • qwen3-1.7b - Small model with thinking (32K context)
  • qwen3-0.6b - Ultra-compact model with thinking (32K context)

​
Qwen2.5 Coder Series

  • qwen2.5-coder-32b-instruct through qwen2.5-coder-0.5b-instruct - Range of coding-optimized models

​
Qwen API Models

  • qwen-coder-plus / qwen-coder-plus-latest - API-hosted coder models
  • qwen-plus / qwen-plus-latest - General-purpose API models with thinking
  • qwen-turbo / qwen-turbo-latest - Fast API models with 1M context
  • qwen-max / qwen-max-latest - Maximum capability API models

​
Vision Models

  • qwen-vl-max / qwen-vl-max-latest - Vision-language max models with image support
  • qwen-vl-plus / qwen-vl-plus-latest - Vision-language plus models

​
Third-Party Models (via Qwen API)

  • deepseek-v3 - DeepSeek V3 hosted on Qwen infrastructure
  • deepseek-r1 - DeepSeek R1 reasoning model

​
Configuration in Cline

  1. Open Cline Settings: Click the settings icon (⚙️) in the Cline panel.
  2. Select Provider: Choose “Alibaba Qwen” from the “API Provider” dropdown.
  3. Select Region: Choose “International” or “China” based on your location.
  4. Enter API Key: Paste your Qwen API key into the “Qwen API Key” field.
  5. Select Model: Choose your desired model from the “Model” dropdown.

​
Thinking / Reasoning Support

Qwen3 models support hybrid thinking with configurable thinking budgets. When enabled, models generate step-by-step reasoning before providing answers, improving performance on complex coding and math tasks.

​
Tips and Notes

  • Region Selection: International and China regions have the same model lineup but may differ in pricing and latency.
  • Thinking Models: Qwen3 models with thinking support have separate output pricing for thinking tokens.
  • Coder Models: Qwen3 Coder Plus offers 1M context window, ideal for large codebases.
  • Vision Support: VL (Vision-Language) models support image inputs for multimodal tasks.
  • Pricing: Check the Alibaba Cloud Bailian Console for current pricing.