Qwen iconQwen: Qwen Plus 0728

Model Type

Proprietary model icon

Proprietary Model

API access only

Recommended Use Cases

Text Generation

Try Qwen Plus 0728

Qwen Plus 0728 is Alibaba's balanced proprietary model offering strong performance, cost efficiency, and 1M token context, positioned between Qwen-Max and Qwen-Flash in the API model lineup.

A balanced model that offers performance, cost, and speed between those of Qwen-Max and Qwen-Flash.

  • Alibaba Cloud

Overview

Qwen-Plus-0728 (qwen-plus-2025-07-28) is based on the Qwen3 foundation and represents the July 2025 snapshot of the Qwen-Plus series. It offers a 1M token context window with hybrid thinking support, making it suitable for moderately complex tasks requiring balanced performance and cost.

Key Features

  • 1M context: Million-token context window
  • Hybrid thinking: Toggle between thinking and non-thinking modes
  • Balanced performance: Between Max capability and Flash speed
  • Strong reasoning: Outperforms QwQ on math, code, and logic
  • Multilingual: 100+ languages with strong translation

Technical Specifications

SpecificationValue
ArchitectureProprietary (based on Qwen3)
Context Length1M tokens
Release DateJuly 2025
LicenseProprietary (API only)

Capabilities

  • Reasoning: Significantly outperforms QwQ in thinking mode
  • Agent capabilities: Industry-leading tool calling in both modes
  • Human alignment: Enhanced creative writing, role-playing, multi-turn dialogue
  • General abilities: Better than similar-scale models without reasoning mode

When to Use Qwen-Plus-0728

Choose Qwen-Plus-0728 when you need:

  • Long-context understanding (1M tokens)
  • Balanced performance and cost
  • Hybrid thinking capability
  • Moderately complex reasoning tasks

Choose alternatives when:

  • Maximum capability needed → Qwen3-Max
  • Fastest/cheapest responses → Qwen-Flash
  • Extended reasoning focus → Qwen-Plus-0728 (thinking)

Availability

  • API: Alibaba Cloud Model Studio
  • Web: chat.qwen.ai
  • Open Weights: Not available (proprietary)

Role in Series

Qwen API models by capability:

  1. Qwen-Flash: Fastest, lowest cost
  2. Qwen-Turbo: Fast, cost-effective (legacy, replaced by Flash)
  3. Qwen-Plus-0728: Balanced (this model)
  4. Qwen3-Max: Maximum capability

Links