Qwen-Plus
Copied!
Try AIAdd to Compare
ReasoningText Generation
Overview
ReasoningText Generation
The Qwen3 Plus model features dynamic switching between thinking and non-thinking modes. This version delivers significantly improved multilingual performance (Chinese/English) and enhanced tool-calling in its non-thinking mode. This is a snapshot from July 14, 2025.
Input
Text
Output
Text
Features
Prefix Completion
Function Calling
Cache
Structured Outputs
Batches
Web Search
Pricing
- Input$0.4Per 1M tokens
- Output$1.2Per 1M tokens
- Input(Thinking)$0.4Per 1M tokens
- Output(Thinking)$4Per 1M tokens
Context
Context
131.07K
Max Input
98.30K
Max Output
16.38K
Rate Limits
- RPMRequests Per Minute60
- TPMTokens Per Minute100K
API Reference
Get API KeyCopied!
12345678910111213141516171819202122232425262728293031