Enum Class DashScopeModel.ChatModel

java.lang.Object
java.lang.Enum<DashScopeModel.ChatModel>
com.alibaba.cloud.ai.dashscope.spec.DashScopeModel.ChatModel
All Implemented Interfaces:
Serializable, Comparable<DashScopeModel.ChatModel>, Constable, org.springframework.ai.model.ChatModelDescription, org.springframework.ai.model.ModelDescription
Enclosing class:
DashScopeModel

public static enum DashScopeModel.ChatModel extends Enum<DashScopeModel.ChatModel> implements org.springframework.ai.model.ChatModelDescription
Spring AI Alibaba DashScope implements all models that support the dashscope platform, and only the Qwen series models are listed here. For more model options, refer to: Model List
  • Nested Class Summary

    Nested classes/interfaces inherited from class java.lang.Enum

    Enum.EnumDesc<E extends Enum<E>>
  • Enum Constant Summary

    Enum Constants
    Enum Constant
    Description
     
     
     
     
     
    QVQ is a visual reasoning model that supports visual input and generates thought chains.
    The QwQ inference model trained based on the Qwen2.5-32B model greatly improves the model inference ability through reinforcement learning.
    Tongyi Qianwen Code Model.
     
    The Tongyi Qianwen series is a model with the longest context window, balanced capabilities and low cost.
    The Tongyi Qianwen mathematical model is a language model specifically designed for solving mathematical problems.
    The model supports an 8k tokens context, and to ensure normal use and output, the API limits user input to 6k tokens.
    The model supports a context of 30k tokens.
    The Qwen-Omni model can receive combined inputs of various modalities such as text, images, audio, and video, and generate responses in text or voice forms.
    Compared to the Omniverse model, it supports audio-based streaming input and has a built-in VAD (Voice Activity Detection) function, which can automatically detect the start and end of the user's voice.
    The QWEN-OMNI series models support the input of multiple modalities of data, including video, audio, image, text, and output audio and text qwen-omni
    Tongyi Qianwen new multi-modal understanding generation model, supports text, image, voice, video input understanding and mixed input understanding, with text and voice simultaneous streaming generation ability, multi-modal content understanding speed significantly improved, provides 4 natural dialogue tones, this version is a dynamic update version.
    The capabilities are balanced, with the reasoning effect, cost and speed falling between that of Qwen Max and Qwen Flash.
    The model supports a context of 32k tokens.
    The qwen-vl model can answer based on the pictures you pass in.
    The Tongyi Qianwen OCR model is a model specifically designed for text extraction.
    New multi-modal understanding generation large model trained based on Qwen2.5, supports text, image, voice, and video input understanding as well as mixed input understanding, with text and voice simultaneous streaming generation capabilities.
    The best-performing model in the Qwen series, suitable for complex and multi-step tasks.
    Tongyi Qianwen 3-Omni-Flash multimodal large model, based on Thinker-Talker Mixture of Experts (MoE) architecture, supports efficient understanding of text, images, audio, video and speech generation capability, and can perform text interaction in 119 languages and speech interaction in 20 languages to generate human-like speech for accurate cross-language communication.
    Tongyi Qianwen VL is a text generation model with visual (image) comprehension capabilities.
    Tongyi Qianwen MT Plus is a multilingual language model that supports.
    The QwQ inference model trained based on the Qwen2.5 model has significantly enhanced the model's inference capabilities through reinforcement learning.
  • Field Summary

    Fields
    Modifier and Type
    Field
    Description
    final String
     
  • Method Summary

    Modifier and Type
    Method
    Description
     
     
    Returns the enum constant of this class with the specified name.
    Returns an array containing the constants of this enum class, in the order they are declared.

    Methods inherited from class java.lang.Object

    getClass, notify, notifyAll, wait, wait, wait

    Methods inherited from interface org.springframework.ai.model.ModelDescription

    getDescription, getVersion
  • Enum Constant Details

    • QWEN_PLUS

      public static final DashScopeModel.ChatModel QWEN_PLUS
      The capabilities are balanced, with the reasoning effect, cost and speed falling between that of Qwen Max and Qwen Flash. It is suitable for medium-complex tasks.
    • QWEN_TURBO

      public static final DashScopeModel.ChatModel QWEN_TURBO
      The model supports a context of 32k tokens. To ensure normal use and output, the API limits user input to 30k tokens.
    • QWEN_MAX

      public static final DashScopeModel.ChatModel QWEN_MAX
      The model supports an 8k tokens context, and to ensure normal use and output, the API limits user input to 6k tokens.
    • QWEN3_MAX

      public static final DashScopeModel.ChatModel QWEN3_MAX
      The best-performing model in the Qwen series, suitable for complex and multi-step tasks.
    • QWEN_LONG

      public static final DashScopeModel.ChatModel QWEN_LONG
      The Tongyi Qianwen series is a model with the longest context window, balanced capabilities and low cost. It is suitable for tasks such as long text analysis, information extraction, summary and abstract generation, and classification tagging.
    • QWN_MT_PLUS

      public static final DashScopeModel.ChatModel QWN_MT_PLUS
      Tongyi Qianwen MT Plus is a multilingual language model that supports. Belongs to Qwen3-MT.
    • QWEN_MATH_PLUS

      public static final DashScopeModel.ChatModel QWEN_MATH_PLUS
      The Tongyi Qianwen mathematical model is a language model specifically designed for solving mathematical problems.
    • QWEN_CODER_PLUS

      public static final DashScopeModel.ChatModel QWEN_CODER_PLUS
      Tongyi Qianwen Code Model. The latest Qwen3-Coder-Plus series models are code generation models based on Qwen3, featuring powerful Coding Agent capabilities. They excel at tool invocation and environment interaction, enabling autonomous programming. Their code capabilities are outstanding while also possessing general capabilities.
    • QWEN_MAX_LONGCONTEXT

      public static final DashScopeModel.ChatModel QWEN_MAX_LONGCONTEXT
      The model supports a context of 30k tokens. To ensure normal use and output, the API limits user input to 28k tokens.
    • QWQ_PLUS

      public static final DashScopeModel.ChatModel QWQ_PLUS
      The QwQ inference model trained based on the Qwen2.5 model has significantly enhanced the model's inference capabilities through reinforcement learning. The core indicators of the model's mathematical code (AIME 24/25, LiveCodeBench) as well as some general indicators (IFEval, LiveBench, etc.) have reached the full health level of DeepSeek-R1. qwen3
    • QWEN_3_32B

      public static final DashScopeModel.ChatModel QWEN_3_32B
      The QwQ inference model trained based on the Qwen2.5-32B model greatly improves the model inference ability through reinforcement learning. The core indicators such as the mathematical code of the model (AIME 24/25, LiveCodeBench) and some general indicators (IFEval, LiveBench, etc.) have reached the level of DeepSeek-R1 full blood version, and all indicators significantly exceed the DeepSeek-R1-Distill-Qwen-32B, which is also based on Qwen2.5-32B. qwen3
    • QWEN_OMNI_TURBO

      public static final DashScopeModel.ChatModel QWEN_OMNI_TURBO
      The QWEN-OMNI series models support the input of multiple modalities of data, including video, audio, image, text, and output audio and text qwen-omni
    • QWEN_OMNI_FLASH_REALTIME

      public static final DashScopeModel.ChatModel QWEN_OMNI_FLASH_REALTIME
      Compared to the Omniverse model, it supports audio-based streaming input and has a built-in VAD (Voice Activity Detection) function, which can automatically detect the start and end of the user's voice.
    • QWEN3_OMNI_FLASH

      public static final DashScopeModel.ChatModel QWEN3_OMNI_FLASH
      Tongyi Qianwen 3-Omni-Flash multimodal large model, based on Thinker-Talker Mixture of Experts (MoE) architecture, supports efficient understanding of text, images, audio, video and speech generation capability, and can perform text interaction in 119 languages and speech interaction in 20 languages to generate human-like speech for accurate cross-language communication. The model has powerful command following and system prompt customization functions, flexibly adapts dialogue style and role setting, and is widely used in text creation, voice assistant, multimedia analysis and other scenes to provide a natural and smooth multi-modal interaction experience.
    • QWEN_OMNI_FLASH

      public static final DashScopeModel.ChatModel QWEN_OMNI_FLASH
      The Qwen-Omni model can receive combined inputs of various modalities such as text, images, audio, and video, and generate responses in text or voice forms. It offers multiple anthropomorphic voices and supports voice output in multiple languages and dialects. It can be applied in scenarios such as text creation, visual recognition, and voice assistants.
    • QWEN_OMNI_TURBO_LATEST

      public static final DashScopeModel.ChatModel QWEN_OMNI_TURBO_LATEST
      Tongyi Qianwen new multi-modal understanding generation model, supports text, image, voice, video input understanding and mixed input understanding, with text and voice simultaneous streaming generation ability, multi-modal content understanding speed significantly improved, provides 4 natural dialogue tones, this version is a dynamic update version.
    • QWEN2_5_OMNI_7B

      public static final DashScopeModel.ChatModel QWEN2_5_OMNI_7B
      New multi-modal understanding generation large model trained based on Qwen2.5, supports text, image, voice, and video input understanding as well as mixed input understanding, with text and voice simultaneous streaming generation capabilities. Multi-modal content understanding speed is significantly improved, providing 4 natural dialogue tones.
    • QWEN_VL_MAX

      public static final DashScopeModel.ChatModel QWEN_VL_MAX
      The qwen-vl model can answer based on the pictures you pass in. qwen-vl
    • QWEN3_VL_PLUS

      public static final DashScopeModel.ChatModel QWEN3_VL_PLUS
      Tongyi Qianwen VL is a text generation model with visual (image) comprehension capabilities. It not only can perform OCR (image text recognition), but also can further summarize and reason, such as extracting attributes from product photos and solving problems based on exercise diagrams, etc.
    • QWEN_FLASH

      public static final DashScopeModel.ChatModel QWEN_FLASH
    • QWEN_VL_OCR

      public static final DashScopeModel.ChatModel QWEN_VL_OCR
      The Tongyi Qianwen OCR model is a model specifically designed for text extraction. Compared to the Tongyi Qianwen VL model, it focuses more on the text extraction capabilities for types of images such as documents, tables, test questions, and handwritten text. It can recognize multiple languages, including English, French, Japanese, Korean, German, Russian, and Italian, etc.
    • QVQ_MAX

      public static final DashScopeModel.ChatModel QVQ_MAX
      QVQ is a visual reasoning model that supports visual input and generates thought chains. It demonstrates stronger capabilities in mathematics, programming, visual analysis, creation, and general tasks.
    • DEEPSEEK_R1

      public static final DashScopeModel.ChatModel DEEPSEEK_R1
    • DEEPSEEK_V3

      public static final DashScopeModel.ChatModel DEEPSEEK_V3
    • DEEPSEEK_V3_1

      public static final DashScopeModel.ChatModel DEEPSEEK_V3_1
    • KIMI_K2

      public static final DashScopeModel.ChatModel KIMI_K2
    • GLM_4_6

      public static final DashScopeModel.ChatModel GLM_4_6
  • Field Details

    • value

      public final String value
  • Method Details

    • values

      public static DashScopeModel.ChatModel[] values()
      Returns an array containing the constants of this enum class, in the order they are declared.
      Returns:
      an array containing the constants of this enum class, in the order they are declared
    • valueOf

      public static DashScopeModel.ChatModel valueOf(String name)
      Returns the enum constant of this class with the specified name. The string must match exactly an identifier used to declare an enum constant in this class. (Extraneous whitespace characters are not permitted.)
      Parameters:
      name - the name of the enum constant to be returned.
      Returns:
      the enum constant with the specified name
      Throws:
      IllegalArgumentException - if this enum class has no constant with the specified name
      NullPointerException - if the argument is null
    • getValue

      public String getValue()
    • getName

      public String getName()
      Specified by:
      getName in interface org.springframework.ai.model.ModelDescription