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 Minute
    60
  • TPMTokens Per Minute
    100K

API Reference

Get API Key
Copied!
123456789101112131415161718192021222324252627282930