All Products
Search
Document Center

:Model overview

Last Updated:Aug 20, 2024

Qwen is a series of large language models (LLMs) independently developed by Alibaba Cloud. Qwen can understand and analyze natural language inputs and provide services and assistance across various fields and tasks.

Scenarios

Qwen series uses its powerful language processing capabilities to provide users with efficient and intelligent language services. Its capabilities include but are not limited to text creation, translation, and dialogue simulation. Qwen series is suitable for the following scenarios:

  • Text creation: writes stories, documents, emails, scripts, and poems.

  • Text processing: polishes text and summarizes text.

  • Programming assistance: writes and optimizes code.

  • Translation: provides translation service among various languages such as Chinese, English, Japanese, French, and Spanish.

  • Dialogue simulation: engages in role-playing for interactive dialogues.

  • Data visualization: creates charts and visualizes data.

Overview

Name

Description

Input and output limits

qwen-turbo

An ultra-large language model that supports multiple input languages such as Chinese and English.

This model supports a context of up to 8,000 tokens. To ensure normal model use and output, the maximum number of input tokens is limited to 6,000.

qwen-plus

An improved ultra-large language model that supports multiple input languages such as Chinese and English.

This model supports a context of up to 32,000 tokens. To ensure normal model use and output, the maximum number of input tokens is limited to 30,000.

qwen-max

An 100-billion-parameter ultra-large language model that support multiple input languages such as Chinese and English. The qwen-max model is updated in rolling mode. If you want to use a stable version, use a historical snapshot version. The latest qwen-max model is equivalent to the qwen-max-0428 snapshot and is the API model for Qwen2.5.

This model supports a context of up to 8,000 tokens. To ensure normal model use and output, the maximum number of input tokens is limited to 6,000.

Note

Billing rules and throttling thresholds vary based on the model. For more information about billing rules, throttling thresholds, and how to apply for higher quotas, see Billing.