← Models / Alibaba Cloud / Qwen

Qwen3-Turbo

Budget option. Will no longer receive updates; Alibaba recommends migrating to Qwen-Flash.

chat OpenAI-compatible Function calling 131K context Released 2025

Pricing

Type USD / 1M tokens CNY / 1M tokens
Input $0.007 ¥0.05
Output $0.028 ¥0.2

vs Western Models

Qwen3-Turbo vs GPT-5.2 ($1.75/$14)
100% cheaper input 100% cheaper output
Qwen3-Turbo vs Claude Sonnet 4.6 ($3/$15)
100% cheaper input 100% cheaper output
Qwen3-Turbo vs Gemini 2.5 Pro ($1.25/$10)
99% cheaper input 100% cheaper output

IDE Setup

Cursor

base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
model: qwen3-turbo

Cline

base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
model: qwen3-turbo

Strengths

  • + extremely cheap
  • + fast

Watch Out For

  • ! content censorship
  • ! deprecated in favor of Qwen-Flash

International Access

Direct access: Yes
Latency from US: 200-400ms
Registration: Alibaba Cloud account
Payment: credit card

More from Alibaba Cloud / Qwen

Qwen3.5-Plus Qwen3.5-Flash Qwen3-Max Qwen3-Plus Qwen3 VL 235B

Ready to try Qwen3-Turbo?

Get your API key from the official platform.

Go to Alibaba Cloud / Qwen →