FlagshipAlibaba

Qwen Plus

Qwen Plus is Alibaba's flagship text model featuring a 1 million token context window for handling extensive documents and complex reasoning tasks.

Context 1.0M
Tier Flagship
Input from
$0.260 / 1M tokens
across 1 provider

API Pricing

ProviderInput / 1MOutput / 1MSpeedTTFTUpdated
$0.260$0.78046.4 t/s1.5s4/14/2026

Prices updated daily. Last check: 4/14/2026

Model Details

General

Creator
Alibaba
Family
Qwen
Tier
Flagship
Context Window
1.0M
Modalities
Text

Capabilities

Tool Calling
No
Open Source
No
Aliases
qwen-plus-2025-07-28, qwen-plus-2025-07-28:thinking

Strengths & Limitations

  • 1 million token context window enables processing of very long documents
  • Flagship tier model optimized for complex reasoning tasks
  • Available in thinking mode variant for transparent reasoning
  • Multiple API versions for different use cases
  • Enterprise-grade model backed by Alibaba Cloud infrastructure
  • Specialized for handling extensive text inputs and analysis
  • Strong performance on Chinese and multilingual tasks
  • Text-only model with no image or multimodal input support
  • No tool calling or function execution capabilities
  • Proprietary model with weights not publicly available
  • Limited to Alibaba Cloud ecosystem and select providers
  • Newer than some established flagship models with longer track records

Key Features

1 million token context window
Text input and generation
Thinking mode with reasoning transparency
Multiple model versions and aliases
Streaming response support
Enterprise API access
Multilingual text processing
Long-form document analysis

About Qwen Plus

Qwen Plus is Alibaba's flagship model in the Qwen family, designed for complex text processing and reasoning tasks. As a proprietary model from Alibaba Cloud, it represents the company's most capable offering for enterprise and developer use cases requiring sophisticated language understanding. The model features an extensive 1 million token context window, enabling it to process very long documents, codebases, or conversations while maintaining coherence across the entire input. Qwen Plus is text-only, focusing on language tasks without multimodal capabilities. The model is available through multiple API versions, including a thinking mode variant that provides reasoning transparency. Qwen Plus competes in the flagship tier alongside models like Claude Opus and GPT-4, targeting users who need to work with large-scale text processing, document analysis, and complex reasoning workflows where the extended context window provides significant advantages over models with smaller context limits.

Common Use Cases

Qwen Plus is well-suited for applications requiring extensive context retention, such as analyzing lengthy legal documents, processing large codebases, conducting research across multiple sources, and maintaining coherent conversations over extended interactions. The 1 million token context window makes it particularly valuable for document summarization, academic research, content analysis, and any workflow where maintaining context across very long inputs is critical. Its flagship tier positioning makes it appropriate for complex reasoning tasks, detailed analysis work, and enterprise applications where processing capacity and context retention are priorities over speed or cost optimization.

Frequently Asked Questions

How much does Qwen Plus cost per million tokens?

Qwen Plus pricing varies by provider and may differ between the standard and thinking mode versions. Check the pricing table above for current rates across all available providers.

What is Qwen Plus best used for?

Qwen Plus excels at tasks requiring extensive context retention, such as analyzing very long documents, processing large codebases, conducting multi-document research, and maintaining coherent conversations across extended interactions. Its 1 million token context window makes it ideal for document analysis and complex reasoning tasks.

Does Qwen Plus support tool calling or multimodal inputs?

No, Qwen Plus is a text-only model without tool calling capabilities or support for images and other modalities. It focuses specifically on text processing and reasoning tasks with its large context window as the primary differentiator.