> ## Documentation Index
> Fetch the complete documentation index at: https://docs.powertokens.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# mimo-v2.5 对话补全

> 调用 MIMO 对话补全能力



## OpenAPI

````yaml api-reference/zh-Hans/zmodelChat/mimo/mimo-v2.5.json POST /v1/chat/completions
openapi: 3.0.1
info:
  title: mimo-v2.5
  version: 1.0.0
  description: MIMO 对话补全文档
  license:
    name: Project License
    url: https://github.com/QuantumNous/new-api/blob/main/LICENSE
servers:
  - url: https://api.powertokens.ai
    description: baze API 服务端点
security: []
tags:
  - name: MIMO 对话
    description: MIMO 文本对话
paths:
  /v1/chat/completions:
    post:
      tags:
        - MIMO 对话
      summary: mimo-v2.5
      description: 调用 MIMO 对话补全能力
      operationId: mimoChatCompletions_mimo_v2_5_zh
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
            examples:
              基础调用:
                summary: 基础文本对话
                value:
                  model: mimo-v2.5
                  messages:
                    - role: system
                      content: >-
                        你是 MiMo，由小米开发的 AI 助手。今天是 2025 年 12 月 16 日，星期二。你的知识截止日期为
                        2024 年 12 月。
                    - role: user
                      content: 请介绍一下你自己
                  max_completion_tokens: 1024
                  temperature: 1
                  top_p: 0.95
                  stream: false
                  stop: null
                  frequency_penalty: 0
                  presence_penalty: 0
                  thinking:
                    type: disabled
              流式响应:
                summary: 流式对话响应
                value:
                  model: mimo-v2.5
                  messages:
                    - role: system
                      content: >-
                        你是 MiMo，由小米开发的 AI 助手。今天是 2025 年 12 月 16 日，星期二。你的知识截止日期为
                        2024 年 12 月。
                    - role: user
                      content:
                        - type: text
                          text: 请介绍一下你自己
                  max_completion_tokens: 1024
                  stream: true
              函数调用:
                summary: 带函数调用的对话
                value:
                  model: mimo-v2.5
                  messages:
                    - role: system
                      content: >-
                        你是 MiMo，由小米开发的 AI 助手。今天是 2025 年 12 月 16 日，星期二。你的知识截止日期为
                        2024 年 12 月。
                    - role: user
                      content: 波士顿今天天气怎么样？
                  max_completion_tokens: 1024
                  tools:
                    - type: function
                      function:
                        name: get_current_weather
                        description: 获取指定位置的当前天气
                        parameters:
                          type: object
                          properties:
                            location:
                              type: string
                              description: 城市和省份，例如 北京
                            unit:
                              type: string
                              enum:
                                - celsius
                                - fahrenheit
                          required:
                            - location
                  tool_choice: auto
              联网搜索:
                summary: 带联网搜索的对话
                value:
                  model: mimo-v2.5
                  messages:
                    - role: system
                      content: >-
                        你是 MiMo，由小米开发的 AI 助手。今天是 2025 年 12 月 16 日，星期二。你的知识截止日期为
                        2024 年 12 月。
                    - role: user
                      content: 请介绍一下雷军
                  tools:
                    - type: web_search
                      max_keyword: 3
                      force_search: true
                      limit: 1
                      user_location:
                        type: approximate
                        country: China
                        region: Hubei
                        city: Wuhan
                  max_completion_tokens: 1024
                  temperature: 1
                  top_p: 0.95
                  stream: false
                  stop: null
                  frequency_penalty: 0
                  presence_penalty: 0
                  thinking:
                    type: disabled
              图像输入:
                summary: 带图像输入的对话
                value:
                  model: mimo-v2.5
                  messages:
                    - role: system
                      content: >-
                        你是 MiMo，由小米开发的 AI 助手。今天是 2025 年 12 月 16 日，星期二。你的知识截止日期为
                        2024 年 12 月。
                    - role: user
                      content:
                        - type: image_url
                          image_url:
                            url: >-
                              https://example-files.cnbj1.mi-fds.com/example-files/image/image_example.png
                        - type: text
                          text: 请描述一下图片的内容
                  max_completion_tokens: 1024
              音频输入:
                summary: 带音频输入的对话
                value:
                  model: mimo-v2.5
                  messages:
                    - role: system
                      content: >-
                        你是 MiMo，由小米开发的 AI 助手。今天是 2025 年 12 月 16 日，星期二。你的知识截止日期为
                        2024 年 12 月。
                    - role: user
                      content:
                        - type: input_audio
                          input_audio:
                            data: >-
                              https://example-files.cnbj1.mi-fds.com/example-files/audio/audio_example.wav
                        - type: text
                          text: 请描述一下音频的内容
                  max_completion_tokens: 1024
              视频输入:
                summary: 带视频输入的对话
                value:
                  model: mimo-v2.5
                  messages:
                    - role: system
                      content: >-
                        你是 MiMo，由小米开发的 AI 助手。今天是 2025 年 12 月 16 日，星期二。你的知识截止日期为
                        2024 年 12 月。
                    - role: user
                      content:
                        - type: video_url
                          video_url:
                            url: >-
                              https://example-files.cnbj1.mi-fds.com/example-files/video/video_example.mp4
                          fps: 2
                          media_resolution: default
                        - type: text
                          text: 请描述一下视频的内容
                  max_completion_tokens: 1024
              结构化输出:
                summary: 带结构化输出的对话
                value:
                  model: mimo-v2.5-pro
                  messages:
                    - role: system
                      content: >-
                        你是 MiMo，由小米开发的 AI 助手。今天是 2025 年 12 月 16 日，星期二。你的知识截止日期为
                        2024 年 12 月。
                    - role: user
                      content: >-
                        我叫张三，今年28岁，邮箱是zhangsan@test.com，生日是1996年5月12日。请按照以下JSON格式返回结果。注意：生日必须使用YYYY-MM-DD格式。{"name":
                        "string or null", "age": "int or null", "email": "string
                        or null", "birthday": "string or null"}
                  max_completion_tokens: 1024
                  response_format:
                    type: json_object
              深度思考:
                summary: 带深度思考的对话
                value:
                  model: mimo-v2.5-pro
                  messages:
                    - role: system
                      content: >-
                        你是 MiMo，由小米开发的 AI 助手。今天是 2025 年 12 月 16 日，星期二。你的知识截止日期为
                        2024 年 12 月。
                    - role: user
                      content: 用三句话介绍机器学习。
                  max_completion_tokens: 1024
                  thinking:
                    type: enabled
      responses:
        '200':
          description: 成功。非流式模式返回 JSON；流式模式返回 SSE 事件流。
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatCompletionResponse'
              examples:
                基础调用:
                  summary: 非流式成功响应
                  value:
                    id: 8b51f9e0515949cb8207fbd35ea6ea5c
                    choices:
                      - finish_reason: stop
                        index: 0
                        message:
                          content: >-
                            你好！我是 MiMo，由小米 LLM Core 团队创建的小米 AI
                            助手。我来这里聊天、回答问题以及协助各种任务——无论是提供信息、集思广益，还是进行友好的对话。有什么问题尽管问我，我会尽力帮忙！😊
                          role: assistant
                          tool_calls: null
                    created: 1776848906
                    model: mimo-v2.5-pro
                    object: chat.completion
                    usage:
                      completion_tokens: 72
                      prompt_tokens: 57
                      total_tokens: 129
                      completion_tokens_details:
                        reasoning_tokens: 0
                      prompt_tokens_details: null
                函数调用:
                  summary: 函数调用响应
                  value:
                    id: 8778784df68043e39a2df03258ddeaa5
                    choices:
                      - finish_reason: tool_calls
                        index: 0
                        message:
                          content: ''
                          role: assistant
                          tool_calls:
                            - id: call_b837e211b7764dab9b56f4d8
                              function:
                                arguments: '{"location": "Boston, MA", "unit": "celsius"}'
                                name: get_current_weather
                              type: function
                          reasoning_content: >-
                            The user is asking about the current weather in
                            Boston. I should use the get_current_weather
                            function to get this information. Boston could refer
                            to Boston, MA. I'll call the function with location
                            "Boston, MA" and use celsius as the unit since
                            that's more commonly used in many places, but
                            actually the user didn't specify a unit. Looking at
                            the function parameters, I can choose celsius or
                            fahrenheit. Since Boston is in the US, maybe
                            fahrenheit would be more appropriate? Actually, I
                            should just pick a default or ask. But the
                            instructions say not to ask about optional
                            parameters if there are defaults. There's no default
                            specified in the schema, so I should choose one.
                            I'll go with celsius as it's more standard
                            internationally. Let me call the function.
                    created: 1776849125
                    model: mimo-v2.5-pro
                    object: chat.completion
                    usage:
                      completion_tokens: 196
                      prompt_tokens: 349
                      total_tokens: 545
                      completion_tokens_details:
                        reasoning_tokens: 161
                      prompt_tokens_details: null
                联网搜索:
                  summary: 联网搜索响应
                  value:
                    id: 828d5db56ff748d8b4623d1972c8eca2
                    choices:
                      - finish_reason: stop
                        index: 0
                        message:
                          content: >-
                            根据搜索结果，以下是关于雷军（Jun Lei）的介绍：


                            雷军是中国著名的企业家和科技行业领袖。他在科技行业拥有30年的创业经验，是中国互联网的代表人物和知名企业家。


                            雷军1969年出生于湖北仙桃。他早年就开始创业，1992年参与创办金山软件，1998年出任金山软件CEO，同年还创办了卓越网。2007年金山软件上市后，他卸任总裁兼CEO职务，担任副董事长。


                            随后几年，雷军积极从事天使投资，投资了凡客诚品、多玩、优视科技等多家创新企业。2010年4月6日，他决定重新创业，成立了小米公司，并于2011年8月16日正式发布了第一款小米手机。


                            此外，雷军于2011年7月重返金山，掌管网游与毒霸业务，并于2011年7月11日正式担任金山软件董事长。他的职业生涯还包括投资水羊股份、易点云、药师帮、车车等公司的案例。
                          role: assistant
                          annotations:
                            - type: url_citation
                              url: https://en.shunwei.com/team
                              title: Team – Shunwei
                              summary: >-
                                Jun LEI Founding Partner & Chairman Mr. Lei Jun,
                                with 30 years of entrepreneurial experience in
                                the science and technology industry, is a
                                representative of China's Internet and a
                                well-known entrepreneShe has been involved in
                                investment cases such as Shuiyang Shares
                                (SZ:300740), Edianyun (HK:02416), Yaoshibang
                                (HK:09885), Cheche, Shansong, Royal Xiaohu,
                                Yangteng Innovation, Zhiketong, Yinghe, Chaya
                              site_name: en.shunwei.com
                              publish_time: '2024-10-26T07:37:04+08:00'
                              logo_url: >-
                                https://th.bochaai.com/favicon?domain_url=https://en.shunwei.com/team
                            - type: url_citation
                              url: >-
                                https://max.book118.com/html/2023/0519/7145010064005110.shtm
                              title: 小米公司介绍-20230519110336.pptx-原创力文档
                              summary: >-
                                小米公司介绍第1页/共25页小米创始人:雷军Millet founder: Lei
                                Jun1969年出生于湖北仙桃,于1992年参与创办金山软件,1998年出任金山软件CEO,1998年创办了卓越网。1969
                                born in Hubei Xiantao, in 1992, and participated
                                in the founding of Kingsoft, 1998 served as CEO
                                of golden hill software. In 1998 founded the
                                network of
                                excellence.2007年,金山软件上市后,雷军卸任金山软件总裁兼CEO职务,担任副董事长。2007,
                                Kingsoft listing, Kingsoft chairman and CEO Lei
                                Juns office, served as vice
                                chairman.之后几年,雷军作为天使投资人,投资了凡客诚品、多玩、优视科技等多家创新型企业。After
                                a few years, Lei Jun as an angel investor,
                                invested more, Eslite, superior technology and a
                                number of innovative
                                enterprises.2010年4月6日,雷军选择重新创业,建立了小米公司,并于2011年8月16日正式发布小米手机。In
                                April 6, 2010, Lei choose to venture, a millet
                                company, and officially released millet mobile
                                phone in August 16,
                                2011.2011年7月,雷军重返金山执掌网游与毒霸;2011年7月11日,正式担任金山软件董事长。July
                                2011, Lei Ju
                              site_name: 原创力文档
                              publish_time: '2023-05-23T19:49:37+08:00'
                              logo_url: >-
                                https://th.bochaai.com/favicon?domain_url=https://max.book118.com/html/2023/0519/7145010064005110.shtm
                          tool_calls: null
                    created: 1776849240
                    model: mimo-v2.5-pro
                    object: chat.completion
                    usage:
                      completion_tokens: 387
                      prompt_tokens: 1222
                      total_tokens: 1609
                      completion_tokens_details:
                        reasoning_tokens: 0
                      prompt_tokens_details: null
                      web_search_usage:
                        tool_usage: 3
                        page_usage: 2
                图像输入:
                  summary: 图像输入响应
                  value:
                    id: e27ffa1d3e31434daa71d6b6a83f6e38
                    choices:
                      - finish_reason: length
                        index: 0
                        message:
                          content: >-
                            根据提供的图片，以下是内容的详细描述：


                            **整体氛围**

                            这张图片描绘了一个宁静、神奇且郁郁葱葱的森林场景。它具有一种空灵的气质，可能是通过数字艺术技术或人工智能生成增强的，其特点在于
                          role: assistant
                          tool_calls: null
                          reasoning_content: >-
                            Here's a thinking process that leads to the
                            description:


                            1.  **Analyze the Request:**

                            *   **Input:** An image of a forest scene with a
                            stream, sunlight, and trees.

                            *   **Task:** Describe the content of the image.


                            2.  **Initial Impression & Overall Mood:**

                            *   The image depicts a serene, magical, and lush
                            forest.

                            *   The lighting is dramatic, with sunbeams
                            filtering through the canopy.

                            *   There's a sense of tranquility and nature in its
                            undisturbed state.

                            *   The style looks somewhat photorealistic but
                            possibly enhanced or AI-generated due to the perfect
                            lighting and composition.


                            3.  **Break Down Visual Elements:**


                            *   **Foreground:**

                            *   *Left side:* Large, detailed ferns. They are
                            vibrant green and look wet or dewy.

                            *   *Bottom center/right:* A stream or small river
                            flowing towards the viewer.

                            *   *Water:* The water is clear but reflects the
                            light, creating a shimmering effect. It flows over
                            smooth, moss-covered rocks.

                            *   *Rocks:* Several large, rounded stones are
                            visible in the immediate foreground, covered in
                            thick green moss.


                            *   **Mid-ground:**

                            *   *Trees:* Massive, ancient-looking trees with
                            thick, gnarled trunks and exposed roots. The bark is
                            textured and dark.

                            *   *Vegetation:* More ferns, bushes, and mossy
                            ground cover lining the banks of the stream.

                            *   *Stream path:* The stream winds back into the
                            forest, guiding the eye.


                            *   **Background:**

                            *   *Forest density:* The trees become denser and
                            fade into a misty or foggy atmosphere.

                            *   *Lighting:* This is the most striking feature.
                            "God rays" or crepuscular rays are streaming down
                            from the upper center/right, cutting through the
                            mist and illuminating the scene.

                            *   *Particles:* There are tiny specks floating in
                            the light beams, looking like dust motes, pollen, or
                            perhaps magical sparkles/fireflies.


                            4.  **Structure the Description:**

                            *   **Introduction:** General summary of the scene
                            (misty forest, stream, sunlight).

                            *   **The Lighting (Key Feature):** Describe the
                            sunbeams and atmosphere.

                            *   **The Vegetation (Flora):** Mention the ferns,
                            moss, and ancient trees.

                            *   **The Water (Hydrography):** Describe the
                            stream, rocks, and reflections.

                            *   **Composition/Atmosphere:** Conclude with the
                            overall feeling (peaceful, ethereal).


                            5.  **Drafting the Description (Iterative
                            refinement):**


                            *   *Draft 1 (Mental):* It's a forest with a river.
                            Big trees on the sides. Sun is shining down in
                            beams. There are ferns in the front left. The rocks
                            are mossy. It looks magical.


                            *   *Draft 2 (More detail):* A lush forest scene. A
                            stream flows through the center over mossy rocks. On
                            the left, there are large ferns. The trees are old
                            with twisted branches. The sun is breaking through
                            the canopy, creating bright rays of light. There is
                            mist in the background. It looks like a fantasy
                            setting.


                            *   *Draft 3 (Polished & Descriptive - closer to
                            final output):*

                            *   Start with the atmosphere: "This image depicts a
                            serene and enchanting forest scene..."

                            *   Focus on the light: "...dominated by dramatic
                            shafts of sunlight (god rays) filtering through the
                            dense canopy..."

                            *   Describe the water: "A gentle stream flows
                            through the center, winding over smooth,
                            moss-covered stones..."

                            *   Describe the plants: "Lush vegetation is
                            everywhere, particularly large, detailed ferns in
                            the foreground on the left..."

                            *   Describe the trees: "Ancient trees with thick,
                            gnarled trunks and exposed roots frame the scene..."


                            6.  **Final Polish (Reviewing against the image):**

                            *   *Check:* Did I mention the moss? Yes.

                            *   *Check:* Did I mention the floating particles?
                            Yes, add that detail about the "sparkles" or dust
                            motes.

                            *   *Check:* Is the perspective correct? Yes, low
                            angle looking up the stream.


                            7.  **Final Output Generation:** (This matches the
                            provided good response.)

                            *   "The image displays a breathtaking, ethereal
                            forest scene..."

                            *   Break it down by lighting, vegetation, and
                            water.

                            *   Mention the color palette (greens, browns,
                            golden light).


                            8.  **Formatting:** Use bullet points or paragraphs
                            for readability. (I will use a mix of general
                            description and specific details).
                    created: 1776849330
                    model: mimo-v2.5
                    object: chat.completion
                    usage:
                      completion_tokens: 1024
                      prompt_tokens: 1085
                      total_tokens: 2109
                      completion_tokens_details:
                        reasoning_tokens: 971
                      prompt_tokens_details:
                        cached_tokens: 5
                        image_tokens: 1024
                音频输入:
                  summary: 音频输入响应
                  value:
                    id: 87ee7097c0f7491ea27429efcc21cc26
                    choices:
                      - finish_reason: stop
                        index: 0
                        message:
                          content: ''
                          role: assistant
                          tool_calls: null
                          reasoning_content: >-
                            Good morning. Could you tell me what the weather
                            will be like today?
                    created: 1776849418
                    model: mimo-v2.5
                    object: chat.completion
                    usage:
                      completion_tokens: 17
                      prompt_tokens: 86
                      total_tokens: 103
                      completion_tokens_details:
                        reasoning_tokens: 15
                      prompt_tokens_details:
                        audio_tokens: 25
                        cached_tokens: 45
                视频输入:
                  summary: 视频输入响应
                  value:
                    id: d2c3bd5a08114f78a525e09b69308dc9
                    choices:
                      - finish_reason: stop
                        index: 0
                        message:
                          content: >-
                            视频中有一只白色小猫，长着明亮的蓝眼睛，坐在抛光木地板上。它靠近一扇挂着米色窗帘的窗户，阳光照进来，在地板上投下阴影。背景中可见一盆绿色的盆栽植物，类似于龟背竹。小猫好奇地环顾四周，然后张开嘴喵喵叫。
                          role: assistant
                          tool_calls: null
                          reasoning_content: >-
                            The user wants a description of the video content.


                            1.  **Analyze the video**:

                            *   **Subject**: A white kitten with blue eyes.

                            *   **Setting**: Indoors, near a window. There are
                            beige curtains, a wooden floor, and a green potted
                            plant (Monstera) in the background.

                            *   **Action**: The kitten is sitting on the wooden
                            floor. It's looking slightly to the side. It meows.
                            The lighting is warm and sunny, creating shadows on
                            the floor.

                            *   **Timestamps**:

                            *   00:00 - 00:03: The kitten sits still, looking
                            around, then opens its mouth to meow. The sun casts
                            shadows.


                            2.  **Synthesize the description**:

                            *   Start with the main subject: A white kitten with
                            blue eyes.

                            *   Describe the environment: Sitting on a wooden
                            floor near a window with beige curtains. Sunlight is
                            streaming in. A plant is visible in the background.

                            *   Describe the action: The kitten looks around and
                            meows.

                            *   Mention the atmosphere: Warm, peaceful, sunny.


                            3.  **Draft the response**:

                            The video features a close-up of a white kitten with
                            striking blue eyes sitting on a polished wooden
                            floor. It is positioned near a window draped with
                            light beige curtains. Sunlight streams through the
                            window, casting long shadows on the floor and
                            illuminating the kitten's fur. In the background, a
                            green potted plant, resembling a Monstera, adds a
                            touch of nature to the indoor setting. The kitten
                            looks around curiously and then lets out a meow. The
                            scene is bright and peaceful.


                            4.  **Refine based on specific details**:

                            *   The kitten is white.

                            *   Blue eyes.

                            *   Wooden floor.

                            *   Window with curtains.

                            *   Plant in background.

                            *   Sunlight/Shadows.

                            *   Action: Meowing.


                            5.  **Final Polish**: Combine these points into a
                            coherent paragraph. The video shows a white kitten
                            with blue eyes sitting on a wooden floor in a sunlit
                            room. It's near a window with curtains and a plant
                            in the background. The kitten meows.


                            Let's stick to a descriptive summary.


                            *   **Subject**: White kitten, blue eyes.

                            *   **Location**: Wooden floor, near window,
                            curtains, plant.

                            *   **Action**: Sitting, looking, meowing.

                            *   **Lighting**: Sunny, warm.


                            Construct the final output.
                    created: 1776849614
                    model: mimo-v2.5
                    object: chat.completion
                    usage:
                      completion_tokens: 590
                      prompt_tokens: 1260
                      total_tokens: 1850
                      completion_tokens_details:
                        reasoning_tokens: 514
                      prompt_tokens_details:
                        audio_tokens: 19
                        cached_tokens: 45
                        video_tokens: 1144
                结构化输出:
                  summary: 结构化输出响应
                  value:
                    id: f88d3e6c6b0043b09871487b5c52e4b4
                    choices:
                      - finish_reason: stop
                        index: 0
                        message:
                          content: >-
                            {"name": "Zhang San", "age": 28, "email":
                            "zhangsan@test.com", "birthday": "1996-05-12"}
                          role: assistant
                          tool_calls: null
                    created: 1776850034
                    model: mimo-v2.5-pro
                    object: chat.completion
                    usage:
                      completion_tokens: 41
                      prompt_tokens: 145
                      total_tokens: 186
                      completion_tokens_details:
                        reasoning_tokens: 0
                      prompt_tokens_details: null
                深度思考:
                  summary: 深度思考响应
                  value:
                    id: 7f2cc80f34b541c49f5fcd40ad34bc73
                    choices:
                      - finish_reason: stop
                        index: 0
                        message:
                          content: >-
                            机器学习是人工智能的一个领域，它使计算机能够从数据中学习并提高性能，而无需为每项任务进行显式编程。它使用算法识别模式，并基于输入信息做出决策或预测。这种方法驱动着从个性化推荐到高级医疗诊断等一切应用。
                          role: assistant
                          tool_calls: null
                          reasoning_content: >-
                            Hmm, the user is asking for a concise introduction
                            to machine learning in exactly three sentences. This
                            seems straightforward but requires careful wording
                            to cover the core concepts without oversimplifying
                            or overcomplicating.  \n\nI should start with the
                            basic definition, then mention how it learns from
                            data, and end with its purpose and real-world
                            relevance. The response should flow naturally from
                            \"what it is\" to \"how it works\" to \"why it
                            matters.\"  \n\nKeeping it neutral and factual works
                            best here—no need for examples or jargon. Just three
                            clear, standalone sentences that collectively give a
                            solid overview.
                    created: 1776850089
                    model: mimo-v2.5-pro
                    object: chat.completion
                    usage:
                      completion_tokens: 179
                      prompt_tokens: 60
                      total_tokens: 239
                      completion_tokens_details:
                        reasoning_tokens: 121
                      prompt_tokens_details: null
            text/event-stream:
              schema:
                $ref: '#/components/schemas/ChatCompletionChunk'
              examples:
                流式响应:
                  summary: 流式响应 SSE 事件
                  value: >-
                    data:
                    {"id":"7ccecae1cc6445f395e0d41c85115663","object":"chat.completion.chunk","created":1776849042,"model":"mimo-v2.5-pro","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":null,"tool_calls":null},"logprobs":null,"finish_reason":null,"matched_stop":null}],"usage":null}


                    data:
                    {"id":"7ccecae1cc6445f395e0d41c85115663","choices":[{"delta":{"content":null,"role":null,"tool_calls":null,"reasoning_content":"Okay,
                    the
                    user"},"finish_reason":null,"index":0}],"created":1776849042,"model":"mimo-v2.5-pro","object":"chat.completion.chunk","usage":null}


                    data:
                    {"id":"7ccecae1cc6445f395e0d41c85115663","choices":[{"delta":{"content":null,"role":null,"tool_calls":null,"reasoning_content":"
                    is
                    asking"},"finish_reason":null,"index":0}],"created":1776849042,"model":"mimo-v2.5-pro","object":"chat.completion.chunk","usage":null}


                    data:
                    {"id":"7ccecae1cc6445f395e0d41c85115663","choices":[{"delta":{"content":null,"role":null,"tool_calls":null,"reasoning_content":"
                    me"},"finish_reason":null,"index":0}],"created":1776849042,"model":"mimo-v2.5-pro","object":"chat.completion.chunk","usage":null}


                    ...


                    data:
                    {"id":"7ccecae1cc6445f395e0d41c85115663","choices":[{"delta":{"content":"'m
                    ready","role":null,"tool_calls":null,"reasoning_content":null},"finish_reason":null,"index":0}],"created":1776849044,"model":"mimo-v2.5-pro","object":"chat.completion.chunk","usage":null}


                    data:
                    {"id":"7ccecae1cc6445f395e0d41c85115663","choices":[{"delta":{"content":"
                    to
                    help!","role":null,"tool_calls":null,"reasoning_content":null},"finish_reason":null,"index":0}],"created":1776849044,"model":"mimo-v2.5-pro","object":"chat.completion.chunk","usage":null}


                    data:
                    {"id":"7ccecae1cc6445f395e0d41c85115663","object":"chat.completion.chunk","created":1776849044,"model":"mimo-v2.5-pro","choices":[{"index":0,"delta":{"role":null,"content":null,"reasoning_content":null,"tool_calls":null},"logprobs":null,"finish_reason":"stop","matched_stop":151645}],"usage":null}


                    data:
                    {"id":"7ccecae1cc6445f395e0d41c85115663","choices":[],"created":1776849044,"model":"mimo-v2.5-pro","object":"chat.completion.chunk","usage":{"completion_tokens":123,"prompt_tokens":55,"total_tokens":178,"completion_tokens_details":{"reasoning_tokens":71},"prompt_tokens_details":null}}


                    data: [DONE]
        '400':
          description: 请求参数无效。
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              examples:
                invalid_request:
                  summary: 参数错误
                  value:
                    error:
                      message: messages 是必需的
                      type: invalid_request_error
                      param: messages
                      code: bad_request_body
        '401':
          description: 身份验证失败，例如缺少或无效的 token。
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              examples:
                unauthorized:
                  summary: 未授权
                  value:
                    error:
                      message: 无效的 token
                      type: api_error
                      code: access_denied
                      param: ''
        '429':
          description: 触发频率限制或账户额度不足。
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              examples:
                quota_exceeded:
                  summary: 额度不足或频率受限
                  value:
                    error:
                      message: 账户额度不足，请稍后重试
                      type: api_error
                      code: insufficient_user_quota
                      param: ''
        '500':
          description: 处理请求时发生内部服务器错误。
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              examples:
                internal_error:
                  summary: 内部处理失败
                  value:
                    error:
                      message: 内部处理失败，请稍后重试
                      type: api_error
                      code: gen_relay_info_failed
                      param: ''
      security:
        - BearerAuth: []
components:
  schemas:
    ChatCompletionRequest:
      type: object
      required:
        - model
        - messages
      description: MIMO 对话补全请求体。
      properties:
        model:
          type: string
          description: 要使用的模型 ID
          enum:
            - mimo-v2.5
          example: mimo-v2.5
        messages:
          type: array
          description: 包含到目前为止对话的消息列表。
          minItems: 1
          items:
            $ref: '#/components/schemas/Message'
        frequency_penalty:
          type: number
          nullable: true
          default: 0
          minimum: -2
          maximum: 2
          description: >-
            取值范围在 -2.0 到 2.0 之间的数值。如果该值为正，那么新 token
            会根据其在已有文本中的出现频率受到相应的惩罚，降低模型重复相同内容的可能性。
        presence_penalty:
          type: number
          nullable: true
          default: 0
          minimum: -2
          maximum: 2
          description: >-
            取值范围在 -2.0 到 2.0 之间的数值。如果该值为正，那么新 token
            会根据其是否已在已有文本中出现受到相应的惩罚，从而增加模型谈论新主题的可能性。
        max_completion_tokens:
          type: integer
          nullable: true
          description: >-
            对话补全中可以生成的 token 数的上限，包括可见的输出 token 数和推理 token 数。mimo-v2.5 的默认值为
            32768。所需范围：[1, 131072]
        response_format:
          $ref: '#/components/schemas/ResponseFormat'
        stop:
          description: 最多 4 个序列，当 API 生成到这些序列时会停止继续生成 token。返回的文本中不会包含这些停止序列。
          nullable: true
          default: null
          oneOf:
            - type: string
            - type: array
              items:
                type: string
              maxItems: 4
        stream:
          type: boolean
          nullable: true
          default: false
          description: 如果设置为 true，模型的响应数据会在生成过程中通过 SSE（server-sent events）的形式流式传输到客户端。
        thinking:
          $ref: '#/components/schemas/ThinkingConfig'
        temperature:
          type: number
          minimum: 0
          maximum: 1.5
          default: 1
          description: >-
            要使用的采样温度，介于 0 和 1.5 之间。较高的值（如 0.8）会使输出更加随机，而较低的值（如
            0.2）会使其更加集中和确定性。我们通常建议更改此值或
            top_p，但不要同时更改。在思考模式下，mimo-v2.5-pro、mimo-v2.5 模型不支持自定义 temperature
            参数。即使传入该参数，实际生效值也会被模型强制采用其推荐默认值 1.0。
        tool_choice:
          $ref: '#/components/schemas/ToolChoice'
        top_p:
          type: number
          default: 0.95
          minimum: 0.01
          maximum: 1
          description: >-
            核采样的概率阈值，用于控制模型生成文本的多样性。top_p 值越高，生成的文本多样性越强；top_p 值越低，生成的文本确定性越高。由于
            temperature 和 top_p
            均用于控制生成文本的多样性，建议仅设置其中一个参数。在思考模式下，mimo-v2.5-pro、mimo-v2.5 模型不支持自定义
            top_p 参数。即使传入该参数，实际生效值也会被模型强制采用其推荐默认值 0.95。
        tools:
          type: array
          description: >-
            模型可能调用的工具列表。目前支持 function（函数）和
            web_search（联网搜索）两种工具类型。注意：在思考模式下的多轮工具调用过程中，模型会在返回 tool_calls 字段的同时返回
            reasoning_content 字段。若要继续对话，建议在后续每次请求的 messages 数组中保留所有历史
            reasoning_content，以获得最佳表现。
          items:
            $ref: '#/components/schemas/ToolDefinition'
    ChatCompletionResponse:
      type: object
      description: Chat 响应对象（非流式输出）。
      properties:
        id:
          type: string
          description: 响应的唯一标识符。
        object:
          type: string
          description: 对象类型，仅为 chat.completion。
        created:
          type: integer
          description: 对话补全对象创建时的 Unix 时间戳（以秒为单位）。
        model:
          type: string
          description: 用于生成结果的模型名称。
        choices:
          type: array
          description: 包含生成的回复选项列表。
          items:
            $ref: '#/components/schemas/ChatCompletionChoice'
        usage:
          $ref: '#/components/schemas/Usage'
    ChatCompletionChunk:
      type: object
      description: >-
        Chat 响应 chunk 对象（流式输出）。SSE 流中的每个 `data:` 事件对应一个 ChatCompletionChunk。流通常以
        `data: [DONE]` 结束。
      properties:
        id:
          type: string
          description: 对话补全对象的唯一标识符。每个数据块均使用相同的 ID。
        object:
          type: string
          enum:
            - chat.completion.chunk
          description: 对象类型，仅为 chat.completion.chunk。
        created:
          type: integer
          description: 对话补全对象创建时的 Unix 时间戳（以秒为单位）。每个数据块均使用相同的时间戳。
        model:
          type: string
          description: 用于生成结果的模型。
        choices:
          type: array
          description: 包含生成的回复选项列表。
          items:
            $ref: '#/components/schemas/ChatCompletionChunkChoice'
        usage:
          description: 该对话补全请求的用量信息。
          allOf:
            - $ref: '#/components/schemas/Usage'
          nullable: true
    ErrorResponse:
      type: object
      properties:
        error:
          $ref: '#/components/schemas/ErrorObject'
    Message:
      description: 对话中的一条消息。根据角色的不同，分为五种消息类型：developer、system、user、assistant 和 tool。
      oneOf:
        - $ref: '#/components/schemas/DeveloperMessage'
        - $ref: '#/components/schemas/SystemMessage'
        - $ref: '#/components/schemas/UserMessage'
        - $ref: '#/components/schemas/AssistantRequestMessage'
        - $ref: '#/components/schemas/ToolMessage'
    ResponseFormat:
      type: object
      description: 一个指定模型必须输出的格式的对象。
      oneOf:
        - type: object
          title: Text
          description: 默认响应格式。用于生成文本响应。
          properties:
            type:
              type: string
              enum:
                - text
              description: 所定义的响应格式类型。仅为 text。
          required:
            - type
        - type: object
          title: JSON object
          description: JSON 对象响应格式。请注意，若系统消息或用户消息中未指示模型生成 JSON，模型将不会输出 JSON 格式内容。
          properties:
            type:
              type: string
              enum:
                - json_object
              description: 所定义的响应格式类型。仅为 json_object。
          required:
            - type
    ThinkingConfig:
      type: object
      description: >-
        这个参数用于控制模型是否启用思维链。注意：在思考模式下的多轮工具调用过程中，模型会在返回 tool_calls 字段的同时返回
        reasoning_content 字段。若要继续对话，建议在后续每次请求的 messages 数组中保留所有历史
        reasoning_content，以获得最佳表现。在思考模式下，mimo-v2.5-pro、mimo-v2.5 模型不支持自定义
        temperature 和 top_p 参数。即使传入该参数，实际生效值也会被模型强制采用其推荐默认值 1.0 和 0.95。
      properties:
        type:
          type: string
          enum:
            - enabled
            - disabled
          default: enabled
          description: 是否启用思维链。mimo-v2.5-pro，mimo-v2.5 默认值为 enabled。可选值：enabled，disabled
      required:
        - type
    ToolChoice:
      oneOf:
        - type: string
          enum:
            - auto
      description: >-
        控制模型如何选择工具。注意：当 tool_choice 传入非 auto 值时，后端会默认移除该字段，模型响应行为仍等同于 auto
        模式（该逻辑保留调整的可能性）。可选值：auto
    ToolDefinition:
      oneOf:
        - type: object
          title: 函数工具
          required:
            - type
            - function
          description: 函数工具定义。
          properties:
            type:
              type: string
              enum:
                - function
              description: 工具类型。目前支持 function。
            function:
              type: object
              required:
                - name
              properties:
                name:
                  type: string
                  description: 工具函数的名称。必须由 a-z、A-Z、0-9 组成，或包含下划线（_）和连字符（-），最大长度为 64。
                description:
                  type: string
                  description: 函数功能的描述，供模型判断何时以及如何调用该函数。
                parameters:
                  type: object
                  description: 函数接受的参数，以 JSON 模式对象的形式描述。若省略 parameters，则表示该函数的参数列表为空。
                  additionalProperties: true
                strict:
                  type: boolean
                  default: false
                  description: >-
                    生成函数调用时是否启用严格的模式遵循。若设为 true，模型将严格遵循 parameters 字段中定义的确切模式。当
                    strict 为 true 时，仅支持 JSON 模式的一个子集。
        - $ref: '#/components/schemas/WebSearchTool'
    ChatCompletionChoice:
      type: object
      properties:
        index:
          type: integer
          description: 选项列表中对应选项的索引。
        message:
          $ref: '#/components/schemas/AssistantResponseMessage'
        finish_reason:
          type: string
          description: >-
            模型停止生成 token 的原因。如果模型到达自然停止点或提供的停止序列，则为 stop；如果达到请求中指定的最大 token 数，则为
            length；如果模型调用了工具，则为 tool_calls。如果内容因触发过滤策略而被拦截，则为
            content_filter；如果模型检测到了复读，则为 repetition_truncation。
    Usage:
      type: object
      description: 该对话补全请求的用量信息。
      properties:
        prompt_tokens:
          type: integer
          description: 提示词使用的 token 数量。
        completion_tokens:
          type: integer
          description: 模型输出内容花费的 token。
        total_tokens:
          type: integer
          description: 请求中使用的 token 总数（提示词 + 补全结果）。
        completion_tokens_details:
          type: object
          description: 补全中使用的 token 数量明细。
          properties:
            reasoning_tokens:
              type: integer
              description: 模型为推理生成的 token 数量。
        prompt_tokens_details:
          type: object
          description: 提示中使用的 token 数量明细。
          properties:
            cached_tokens:
              type: integer
              description: 命中缓存的 token 数量。
            audio_tokens:
              type: integer
              description: 提示中存在的音频输入 token 数量。
            image_tokens:
              type: integer
              description: 提示中存在的图像输入 token 数量。
            video_tokens:
              type: integer
              description: 提示中存在的视频输入 token 数量。
        web_search_usage:
          type: object
          description: 联网搜索 API 的调用量明细。
          properties:
            tool_usage:
              type: integer
              description: 联网搜索 API 的调用次数。
            page_usage:
              type: integer
              description: 联网搜索 API 返回的网页数。
    ChatCompletionChunkChoice:
      type: object
      description: Chat 响应 chunk 对象（流式输出）。
      properties:
        index:
          type: integer
          description: 选项列表中对应选项的索引。
        delta:
          type: object
          description: 流式模型响应生成的对话补全增量。
          properties:
            role:
              type: string
              description: 消息作者的角色。
            content:
              type: string
              description: 数据块消息的内容。
            reasoning_content:
              type: string
              description: 助手消息中最终答案之前的推理内容。
            tool_calls:
              type: array
              description: 函数调用启动后，模型会返回待调用的工具以及该调用所需的参数。此参数可包含一个或多个工具响应对象。
              items:
                type: object
                properties:
                  index:
                    type: integer
                    description: 在 tool_calls 列表中被调用工具的索引，从 0 开始。
                  id:
                    type: string
                    description: 工具调用的 ID。
                  type:
                    type: string
                    enum:
                      - function
                    description: 工具的类型。目前仅支持 function。
                  function:
                    type: object
                    description: 调用的函数。
                    properties:
                      name:
                        type: string
                        description: 要调用的函数的名称。
                      arguments:
                        type: string
                        description: >-
                          模型生成的用于调用函数的参数，格式为 JSON。请注意，模型生成的内容并非并非总能保证是有效的
                          JSON，且可能会虚构出函数模式中未定义的参数。在调用函数之前，请在代码中对这些参数进行验证。
            annotations:
              type: array
              description: 联网搜索后，模型会返回全部引用网址的注释。
              items:
                $ref: '#/components/schemas/Annotation'
            error_message:
              type: string
              description: 联网搜索链路的错误信息。
        finish_reason:
          type: string
          nullable: true
          description: >-
            模型停止生成 token 的原因。如果模型到达自然停止点或提供的停止序列，则为 stop；如果达到请求中指定的最大 token 数，则为
            length；如果模型调用了工具，则为 tool_calls。如果内容因触发过滤策略而被拦截，则为
            content_filter；如果模型检测到了复读，则为 repetition_truncation。
    ErrorObject:
      type: object
      properties:
        message:
          type: string
          description: 错误描述。
        type:
          type: string
          description: 错误类型。
        param:
          type: string
          description: 关联字段名称。
        code:
          type: string
          description: 错误代码。
    DeveloperMessage:
      type: object
      title: Developer message · object
      required:
        - role
        - content
      description: 开发者消息。开发者提供的指令，无论用户发送什么消息，模型都应遵循这些指令。
      properties:
        role:
          type: string
          enum:
            - developer
          description: 消息作者的角色，为 developer。
        content:
          description: 开发者消息的内容。
          oneOf:
            - type: string
              description: 纯文本内容。
            - $ref: '#/components/schemas/TextContentPartArray'
        name:
          type: string
          description: 参与者的可选名称，提供给模型以区分同一角色的不同参与者。
    SystemMessage:
      title: System message · object
      type: object
      required:
        - role
        - content
      description: 系统消息。此消息的角色为 system。
      properties:
        content:
          description: 系统消息的内容。
          oneOf:
            - type: string
              description: 纯文本内容。
            - $ref: '#/components/schemas/TextContentPartArray'
        role:
          type: string
          enum:
            - system
          description: 消息作者的角色，为 system。
        name:
          type: string
          description: 参与者的可选名称，提供给模型以区分同一角色的不同参与者。
    UserMessage:
      title: User message · object
      type: object
      required:
        - role
        - content
      description: 用户消息。此消息的角色为 user。
      properties:
        content:
          description: 用户消息的内容。
          oneOf:
            - type: string
              description: 纯文本内容。
            - $ref: '#/components/schemas/ContentPartArray'
        role:
          type: string
          enum:
            - user
          description: 消息作者的角色，为 user。
        name:
          type: string
          description: 参与者的可选名称，提供给模型以区分同一角色的不同参与者。
    AssistantRequestMessage:
      title: Assistant message · object
      type: object
      required:
        - role
      description: 助手消息。此消息的角色为 assistant。
      properties:
        content:
          description: 助手消息的内容。除非指定了 tool_calls，否则为必需。
          oneOf:
            - type: string
              nullable: true
              description: 纯文本内容。
            - $ref: '#/components/schemas/TextContentPartArray'
        role:
          type: string
          enum:
            - assistant
          description: 消息作者的角色，为 assistant。
        name:
          type: string
          description: 参与者的可选名称，提供给模型以区分同一角色的不同参与者。
        tool_calls:
          type: array
          description: 模型生成的工具调用，如函数调用。
          items:
            $ref: '#/components/schemas/ToolCallMessage'
    ToolMessage:
      title: Tool message · object
      type: object
      required:
        - role
        - content
        - tool_call_id
      description: 工具消息。此消息的角色为 tool。
      properties:
        role:
          type: string
          enum:
            - tool
          description: 消息作者的角色，为 tool。
        content:
          description: 工具消息的内容。
          oneOf:
            - type: string
              description: 工具消息的文本内容。
            - $ref: '#/components/schemas/TextContentPartArray'
        tool_call_id:
          type: string
          description: 此消息所响应的工具调用的 ID。
    WebSearchTool:
      type: object
      required:
        - type
      description: 联网搜索工具对象。详情请参考联网搜索文档。注意：使用前需要开通联网服务插件。暂不支持联网搜索工具。
      properties:
        user_location:
          $ref: '#/components/schemas/WebSearchUserLocation'
        type:
          type: string
          enum:
            - web_search
          description: 工具类型。必须为 web_search。
        force_search:
          type: string
          default: 'false'
          description: 是否启用强制搜索。true 强制搜索，false 由模型判断是否需要搜索。
        max_keyword:
          type: integer
          default: 5
          minimum: 1
          maximum: 50
          description: 限制单轮搜索中可使用的最大关键词数量。
        limit:
          type: integer
          default: 5
          minimum: 1
          maximum: 50
          description: 限制单次搜索操作返回的最大结果条数。
      title: 联网搜索工具
    AssistantResponseMessage:
      type: object
      description: 模型生成的对话补全消息。
      properties:
        role:
          type: string
          description: 消息作者的角色。
        content:
          type: string
          description: 消息的内容。
        reasoning_content:
          type: string
          description: 助手消息中最终答案之前的推理内容。
        tool_calls:
          type: array
          description: 函数调用启动后，模型会返回待调用的工具以及该调用所需的参数。此参数可包含一个或多个工具响应对象。
          items:
            oneOf:
              - $ref: '#/components/schemas/ToolCallMessage'
        annotations:
          type: array
          description: 联网搜索后，模型会返回全部引用网址的注释。
          items:
            $ref: '#/components/schemas/Annotation'
        error_message:
          type: string
          description: 联网搜索的错误信息。
        audio:
          $ref: '#/components/schemas/AudioResponse'
        final_text_preview:
          type: string
          description: 经过智能优化润色后的音频播报最终文本。仅当请求参数 optimize_text_preview 设为 true 时，该字段才会返回。
    Annotation:
      type: object
      description: 联网搜索后，模型会返回全部引用网址的注释。
      properties:
        logo_url:
          type: string
          description: logo 网址。
        publish_time:
          type: string
          description: 发布时间。
        site_name:
          type: string
          description: 网站名称。
        summary:
          type: string
          description: 总结。
        title:
          type: string
          description: 标题。
        type:
          type: string
          description: 类型。
        url:
          type: string
          description: 网址。
    TextContentPartArray:
      type: array
      description: 消息中的纯文本内容部分数组。
      items:
        $ref: '#/components/schemas/TextContentPart'
      title: Array of content parts · array
    ContentPartArray:
      type: array
      description: 用户消息中内容部分的数组。可包含文本、图像、音频或视频。
      items:
        oneOf:
          - $ref: '#/components/schemas/ContentPartText'
          - $ref: '#/components/schemas/ContentPartImage'
          - $ref: '#/components/schemas/ContentPartAudio'
          - $ref: '#/components/schemas/ContentPartVideo'
    ToolCallMessage:
      type: object
      description: 消息中的工具调用对象。
      properties:
        id:
          type: string
          description: 工具调用的 ID。
        type:
          type: string
          enum:
            - function
          description: 工具的类型。目前仅支持 function。
        function:
          type: object
          description: 模型所调用的函数。
          properties:
            name:
              type: string
              description: 模型所调用的函数的名称。
            arguments:
              type: string
              description: >-
                模型生成的用于调用函数的参数，格式为 JSON 字符串。请注意，模型生成的内容并非总能保证是有效的
                JSON，且可能会虚构出函数模式中未定义的参数。在调用函数之前，请在代码中对这些参数进行验证。
      title: Function tool call · object
    WebSearchUserLocation:
      type: object
      required:
        - type
        - country
      description: 用户地理位置，用于优化模型输出结果。
      properties:
        type:
          type: string
          enum:
            - approximate
          description: 位置类型，必须为 approximate。
        country:
          type: string
          description: 国家
        region:
          type: string
          description: 省份
        city:
          type: string
          description: 城市
        district:
          type: string
          description: 区县
        longitude:
          type: number
          format: double
          description: 经度
        latitude:
          type: number
          format: double
          description: 纬度
    AudioResponse:
      type: object
      description: 如果请求输出音频，该对象将包含有关模型音频响应的数据。
      properties:
        id:
          type: string
          description: 此音频响应的唯一标识符。
        data:
          type: string
          description: 模型生成的 Base64 编码音频，格式为请求中指定的格式。
        expires_at:
          type: number
          nullable: true
          description: 此音频响应过期的 Unix 时间戳（以秒为单位）。当前仅为 null。
        transcript:
          type: string
          nullable: true
          description: 模型生成的音频的文字记录。当前仅为 null。
    TextContentPart:
      type: object
      title: Text content part · object
      required:
        - type
        - text
      description: 消息中的纯文本内容部分。
      properties:
        type:
          type: string
          enum:
            - text
          description: 内容部分的类型，为 text。
        text:
          type: string
          description: 文本内容。
    ContentPartText:
      type: object
      title: Text content part · object
      required:
        - type
        - text
      description: 用户消息中的纯文本内容部分。
      properties:
        type:
          type: string
          enum:
            - text
          description: 内容部分的类型，为 text。
        text:
          type: string
          description: 文本内容。
    ContentPartImage:
      type: object
      title: Image content part · object
      required:
        - type
        - image_url
      description: 用户消息中的图片内容部分。
      properties:
        type:
          type: string
          enum:
            - image_url
          description: 内容部分的类型，为 image_url。
        image_url:
          type: object
          required:
            - url
          description: 图片 URL。可以是公共图片 URL 或 Base64 编码的数据 URL。
          properties:
            url:
              type: string
              format: uri
              description: 公共图片 URL 或 Base64 编码的数据 URL。
    ContentPartAudio:
      type: object
      title: Audio content part · object
      required:
        - type
        - input_audio
      description: 用户消息中的音频内容部分。
      properties:
        type:
          type: string
          enum:
            - input_audio
          description: 内容部分的类型，类型值为 input_audio。
        input_audio:
          type: object
          required:
            - data
          description: 音频的 URL 或 Base64 编码的音频数据。
          properties:
            data:
              type: string
              description: 音频的 URL 或 Base64 编码的音频数据。
    ContentPartVideo:
      type: object
      title: Video content part · object
      required:
        - type
        - video_url
      description: 用户消息中的视频内容部分。
      properties:
        type:
          type: string
          enum:
            - video_url
          description: 内容部分的类型，值为 video_url。
        video_url:
          type: object
          required:
            - url
          description: 视频 URL。可以是公共视频 URL 或 Base64 编码的数据 URL。
          properties:
            url:
              type: string
              format: uri
              description: 视频的 URL 或 Base64 编码的视频数据。
            fps:
              type: number
              default: 2
              description: 每秒抽帧数。所需范围：[0.1, 10.0]
            media_resolution:
              type: string
              default: default
              enum:
                - default
                - max
              description: 分辨率档次。可选值：default，max
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API Token
      description: '在请求头中传递 `Authorization: Bearer <token>`。'

````