Zhipu AI Paas API

openapi: 3.2.0
info:
  title: Z.AI Agents Paas API
  description: Z.AI API available endpoints
  license:
    name: Z.AI Developer Agreement and Policy
    url: https://chat.z.ai/legal-agreement/terms-of-service
  version: 1.0.0
  contact:
    name: Z.AI Developers
    url: https://chat.z.ai/legal-agreement/privacy-policy
    email: user_feedback@z.ai
servers:
- url: https://api.z.ai/api
  description: Production server
security:
- bearerAuth: []
tags:
- name: Paas
paths:
  /paas/v4/chat/completions:
    post:
      description: Create a chat completion model that generates AI replies for given conversation messages. It supports multimodal inputs (text, images, audio, video, file), offers configurable parameters (like temperature, max tokens, tool use), and supports both streaming and non-streaming output modes.
      parameters:
      - $ref: '#/components/parameters/AcceptLanguage'
      requestBody:
        content:
          application/json:
            schema:
              oneOf:
              - title: Text Model
                $ref: '#/components/schemas/ChatCompletionTextRequest'
              - title: Vision Model
                $ref: '#/components/schemas/ChatCompletionVisionRequest'
            examples:
              Basic Example:
                value:
                  model: glm-5.1
                  messages:
                  - role: system
                    content: You are a useful AI assistant.
                  - role: user
                    content: Please tell us about the development of artificial intelligence.
                  temperature: 1
                  stream: false
              Stream Example:
                value:
                  model: glm-5.1
                  messages:
                  - role: user
                    content: Write a poem about spring.
                  temperature: 1
                  stream: true
              Thinking Example:
                value:
                  model: glm-5.1
                  messages:
                  - role: user
                    content: Write a poem about spring.
                  thinking:
                    type: enabled
                  stream: true
              Multi Conversation:
                value:
                  model: glm-5.1
                  messages:
                  - role: system
                    content: You are a professional programming assistant.
                  - role: user
                    content: What is recursion?
                  - role: assistant
                    content: Recursion is a programming technique where a function calls itself to solve a problem... What is recursion
                  - role: user
                    content: Can you give me an example of Python recursion?
                  stream: true
              Image Visual Example:
                value:
                  model: glm-5v-turbo
                  messages:
                  - role: user
                    content:
                    - type: image_url
                      image_url:
                        url: https://cdn.bigmodel.cn/static/logo/register.png
                    - type: image_url
                      image_url:
                        url: https://cdn.bigmodel.cn/static/logo/api-key.png
                    - type: text
                      text: What are the pics talk about?
              Video Visual Example:
                value:
                  model: glm-5v-turbo
                  messages:
                  - role: user
                    content:
                    - type: video_url
                      video_url:
                        url: https://cdn.bigmodel.cn/agent-demos/lark/113123.mov
                    - type: text
                      text: What are the video show about?
              File Visual Example:
                value:
                  model: glm-5v-turbo
                  messages:
                  - role: user
                    content:
                    - type: file_url
                      file_url:
                        url: https://cdn.bigmodel.cn/static/demo/demo2.txt
                    - type: file_url
                      file_url:
                        url: https://cdn.bigmodel.cn/static/demo/demo1.pdf
                    - type: text
                      text: What are the files show about?
              Function Call Example:
                value:
                  model: glm-5.1
                  messages:
                  - role: user
                    content: Is there an example of how the weather in Beijing is today?
                  tools:
                  - type: function
                    function:
                      name: get_weather
                      description: Get weather information for the specified city.
                      parameters:
                        type: object
                        properties:
                          city:
                            type: string
                            description: City Name
                        required:
                        - city
                  tool_choice: auto
                  temperature: 0.3
        required: true
      responses:
        '200':
          description: Processing successful
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatCompletionResponse'
        default:
          description: The request has failed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
      tags:
      - Paas
  /paas/v4/videos/generations:
    post:
      description: 'CogVideoX is a video generation large model developed by Z.AI, equipped with powerful video generation capabilities. Simply inputting text or images allows for effortless video creation.


        Vidu: A high-performance video large model that combines high consistency and high dynamism, with precise semantic understanding and exceptional reasoning speed.'
      parameters:
      - $ref: '#/components/parameters/AcceptLanguage'
      requestBody:
        content:
          application/json:
            schema:
              oneOf:
              - title: CogVideoX-3
                $ref: '#/components/schemas/CogVideoX3Request'
              - title: 'Vidu: Text to Video'
                $ref: '#/components/schemas/ViduText2VideoRequest'
              - title: 'Vidu: Image to Video'
                $ref: '#/components/schemas/ViduImage2VideoRequest'
              - title: 'Vidu: First & Last Frame to Video'
                $ref: '#/components/schemas/ViduFrames2VideoRequest'
              - title: 'Vidu: Ref to Video'
                $ref: '#/components/schemas/ViduReference2VideoRequest'
            examples:
              Text to Video Example:
                value:
                  model: cogvideox-3
                  prompt: A cat is playing with a ball.
                  quality: quality
                  with_audio: true
                  size: 1920x1080
                  fps: 30
              Image to Video Example:
                value:
                  model: cogvideox-3
                  image_url: https://img.iplaysoft.com/wp-content/uploads/2019/free-images/free_stock_photo.jpg
                  prompt: Make the picture move
                  quality: quality
                  with_audio: true
                  size: 1920x1080
                  fps: 30
              First Last Frame to Video:
                value:
                  model: cogvideox-3
                  image_url:
                  - https://gd-hbimg.huaban.com/ccee58d77afe8f5e17a572246b1994f7e027657fe9e6-qD66In_fw1200webp
                  - https://gd-hbimg.huaban.com/cc2601d568a72d18d90b2cc7f1065b16b2d693f7fa3f7-hDAwNq_fw1200webp
                  prompt: Make the picture move
                  quality: quality
                  with_audio: true
                  size: 1920x1080
                  fps: 30
        required: true
      responses:
        '200':
          description: Processing successful.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VideoResponse'
        default:
          description: The request has failed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
      tags:
      - Paas
  /paas/v4/async-result/{id}:
    get:
      description: This endpoint is used to query the result of an asynchronous request.
      parameters:
      - $ref: '#/components/parameters/AcceptLanguage'
      - name: id
        in: path
        required: true
        schema:
          type: string
          description: Task id.
      responses:
        '200':
          description: Processing successful
          content:
            application/json:
              schema:
                oneOf:
                - title: Video Generation
                  $ref: '#/components/schemas/AsyncVideoGenerationResponse'
                - title: Image Generation
                  $ref: '#/components/schemas/AsyncImageGenerationResponse'
        default:
          description: The request has failed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
      tags:
      - Paas
  /paas/v4/images/generations:
    post:
      summary: Generate Image
      description: Use [GLM-Image](/guides/image/glm-image) series models to generate high-quality images from text prompts. Through quick and accurate understanding of user text descriptions, `AI` image expression becomes more precise and personalized.
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateImageRequest'
            examples:
              Generate Image Example:
                value:
                  model: glm-image
                  prompt: A cute little kitten sitting on a sunny windowsill, with the background of blue sky and white clouds.
                  size: 1280x1280
        required: true
      responses:
        '200':
          description: Processing successful
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ImageGenerationResponse'
        default:
          description: Request Failed
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
      tags:
      - Paas
  /paas/v4/async/images/generations:
    post:
      summary: Generate Image (Async)
      description: Use the [GLM-Image](/guides/image/glm-image) series models to generate high-quality images from text prompts. Through quick and accurate understanding of user text descriptions, `AI` image expression becomes more precise and personalized. Only supports `GLM-Image` model.
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/AsyncCreateImageRequest'
            examples:
              Image Generation Example:
                value:
                  model: glm-image
                  prompt: A cute little kitten sitting on a sunny windowsill, with the background of blue sky and white clouds.
                  size: 1280x1280
        required: true
      responses:
        '200':
          description: Processing successful
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AsyncResponse'
        default:
          description: The request has failed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
      tags:
      - Paas
  /paas/v4/audio/transcriptions:
    post:
      summary: Speech to Text
      description: Use the [GLM-ASR-2512](/guides/audio/glm-asr-2512) model to transcribe audio files into text, supporting multiple languages and real-time streaming transcription.
      requestBody:
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/AudioTranscriptionRequest'
            example:
              model: glm-asr-2512
              stream: false
        required: true
      responses:
        '200':
          description: Request processed successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AudioTranscriptionResponse'
            text/event-stream:
              schema:
                $ref: '#/components/schemas/AudioTranscriptionStreamResponse'
        default:
          description: Request failed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
      tags:
      - Paas
  /paas/v4/tokenizer:
    post:
      summary: Text Tokenizer
      description: '`Tokenizer` is used to split text into `tokens` recognizable by the model and calculate the count. It receives user input text, processes it through the model for tokenization, and finally returns the corresponding `token` count. It is suitable for text length evaluation, model input estimation, dialogue context truncation, cost calculation, etc.'
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/TokenizerRequest'
            examples:
              Text Tokenization Example:
                value:
                  model: glm-4.6
                  messages:
                  - role: user
                    content: What opportunities and challenges will the Chinese large model industry face in 2025?
        required: true
      responses:
        '200':
          description: Business processing successful
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TokenizerResponse'
        default:
          description: The request has failed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
      tags:
      - Paas
  /paas/v4/layout_parsing:
    post:
      summary: Layout Parsing
      description: Use the [GLM-OCR](/guides/vlm/glm-ocr) model to parse the layout of documents and images and extract text content. Support OCR recognition of images and PDF documents, returning detailed layout information and visualization results.
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/LayoutParsingRequest'
            examples:
              Layout Parsing Example:
                value:
                  model: glm-ocr
                  file: https://cdn.bigmodel.cn/static/logo/introduction.png
        required: true
      responses:
        '200':
          description: Business processing successful
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/LayoutParsingResponse'
        default:
          description: Request failed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
      tags:
      - Paas
  /paas/v4/web_search:
    post:
      description: The [Web Search](/guides/tools/web-search) is a specialized search engine for large language models. Building upon traditional search engine capabilities like web crawling and ranking, it enhances intent recognition to return results better suited for LLM processing (including webpage titles, URLs, summaries, site names, favicons etc.).
      parameters:
      - $ref: '#/components/parameters/AcceptLanguage'
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/WebSearchRequest'
        required: true
      responses:
        '200':
          description: Processing successful
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/WebSearchResponse'
        default:
          description: The request has failed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
      tags:
      - Paas
  /paas/v4/files:
    post:
      description: This API is designed for uploading auxiliary files (such as glossaries, terminology lists) to support the translation service. It allows users to upload reference materials that can enhance translation accuracy and consistency.
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                purpose:
                  type: string
                  description: Upload purpose (agent)
                  default: agent
                  enum:
                  - agent
                file:
                  type: string
                  format: binary
                  description: 'File to upload. Limit to `100MB`. Allowed formats: `pdf`, `doc`, `xlsx`, `ppt`, `txt`, `jpg`, `png`.'
              required:
              - purpose
              - file
        required: true
      responses:
        '200':
          description: Processing successful
          content:
            application/json:
              schema:
                type: object
                properties:
                  id:
                    type: string
                    description: Unique identifier of the uploaded file.
                  object:
                    type: string
                    description: Object type.
                  bytes:
                    type: integer
                    description: File size in bytes.
                  filename:
                    type: string
                    description: Name of the uploaded file.
                  purpose:
                    type: string
                    description: Purpose of the uploaded file.
                  created_at:
                    type: integer
                    description: Timestamp of file creation.
        default:
          description: The request has failed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
      tags:
      - Paas
components:
  schemas:
    ChatCompletionResponseMessage:
      type: object
      properties:
        role:
          type: string
          description: Current conversation role, default is ‘assistant’ (model)
          example: assistant
        content:
          type: string
          description: "Current conversation content. Hits function is null, otherwise returns model inference result. \nFor the GLM-4.5V series models, the output may contain the reasoning process tags `<think> </think>` or the text boundary tags `<|begin_of_box|> <|end_of_box|>`."
        reasoning_content:
          type: string
          description: Reasoning content, supports by GLM-4.5 series.
        tool_calls:
          type: array
          description: Function names and parameters generated by the model that should be called.
          items:
            $ref: '#/components/schemas/ChatCompletionResponseMessageToolCall'
    VideoCommonRequest:
      type: object
      properties:
        request_id:
          type: string
          description: Provided by the client, must be unique; used to distinguish each request’s unique identifier. If not provided by the client, the platform will generate one by default.
        user_id:
          type: string
          description: 'Unique ID of the end-user, assists the platform in intervening in end-user violations, generating illegal or inappropriate information, or other abusive behaviors. ID length requirement: minimum `6` characters, maximum `128` characters.'
    WebSearchToolSchema:
      type: object
      title: Web Search
      properties:
        type:
          type: string
          default: web_search
          enum:
          - web_search
        web_search:
          $ref: '#/components/schemas/WebSearchObject'
      required:
      - type
      - web_search
      additionalProperties: false
    FunctionObject:
      type: object
      properties:
        name:
          type: string
          description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
          minLength: 1
          maxLength: 64
          pattern: ^[a-zA-Z0-9_-]+$
        description:
          type: string
          description: A description of what the function does, used by the model to choose when and how to call the function.
        parameters:
          $ref: '#/components/schemas/FunctionParameters'
      required:
      - name
      - description
      - parameters
    ImageGenerationResponse:
      type: object
      properties:
        created:
          type: integer
          example: 1760335349
          description: Request creation time, in `Unix` timestamp format, unit is seconds.
        data:
          type: array
          description: Array, containing the generated image `URL`. Currently, the array only contains one image.
          items:
            type: object
            properties:
              url:
                type: string
                description: Image link. The temporary link expires after `30` days, please store it promptly.
            required:
            - url
        content_filter:
          type: array
          description: Array, containing content safety related information.
          items:
            type: object
            properties:
              role:
                type: string
                description: Safety enforcement stage, including `role = assistant` model inference, `role = user` user input, `role = history` historical context.
                enum:
                - assistant
                - user
                - history
              level:
                type: integer
                description: Severity level `level 0-3`, `level 0` is most severe, `3` is least severe.
                minimum: 0
                maximum: 3
    AudioTranscriptionStreamResponse:
      type: object
      properties:
        id:
          type: string
          description: Task ID
        created:
          type: integer
          format: int64
          description: Request creation time, as a `Unix` timestamp in seconds.
        model:
          type: string
          description: Model name
        type:
          type: string
          description: Audio transcription event type. `transcript.text.delta` indicates transcription in progress, `transcript.text.done` indicates transcription completed.
        delta:
          type: string
          description: Incremental audio transcription information returned by the model.
    ChatCompletionVisionRequest:
      required:
      - model
      - messages
      type: object
      properties:
        model:
          type: string
          description: The model code to be called. GLM-5V-Turbo are the new generation of visual reasoning models. `AutoGLM-Phone-Multilingual` is mobile intelligent assistant model.
          example: glm-5v-turbo
          default: glm-5v-turbo
          enum:
          - glm-5v-turbo
          - glm-4.6v
          - autoglm-phone-multilingual
          - glm-4.6v-flash
          - glm-4.6v-flashx
          - glm-4.5v
        messages:
          type: array
          description: 'The current conversation message list as the model’s prompt input, provided in JSON array format, e.g.,`{“role”: “user”, “content”: “Hello”}`. Possible message types include system messages, user messages. Note: The input must not consist of system or assistant messages only.'
          items:
            oneOf:
            - title: User Message
              type: object
              properties:
                role:
                  type: string
                  enum:
                  - user
                  description: Role of the message author
                  default: user
                content:
                  oneOf:
                  - type: array
                    description: Multimodal message content, supports text, images, video, file
                    items:
                      $ref: '#/components/schemas/VisionMultimodalContentItem'
                  - type: string
                    description: Text message content (can switch to multimodal message above)
                    example: What opportunities and challenges will the Chinese large model industry face in 2025?
              required:
              - role
              - content
            - title: System Message
              type: object
              properties:
                role:
                  type: string
                  enum:
                  - system
                  description: Role of the message author
                  default: system
                content:
                  oneOf:
                  - type: string
                    description: Message text content
                    example: You are a helpful assistant.
              required:
              - role
              - content
            - title: Assistant Message
              type: object
              description: Can include tool calls
              properties:
                role:
                  type: string
                  enum:
                  - assistant
                  description: Role of the message author
                  default: assistant
                content:
                  oneOf:
                  - type: string
                    description: Text message content
                    example: I'll help you with that analysis.
              required:
              - role
          minItems: 1
        request_id:
          type: string
          description: Passed by the user side, needs to be unique; used to distinguish each request. If not provided by the user side, the platform will generate one by default.
        do_sample:
          type: boolean
          example: true
          default: true
          description: When do_sample is true, sampling strategy is enabled; when do_sample is false, sampling strategy parameters such as temperature and top_p will not take effect. Default value is `true`.
        stream:
          type: boolean
          example: false
          default: false
          description: 'This parameter should be set to false or omitted when using synchronous call. It indicates that the model returns all content at once after generating all content. Default value is false. If set to true, the model will return the generated content in chunks via standard Event Stream. When the Event Stream ends, a `data: [DONE]` message will be returned.'
        thinking:
          $ref: '#/components/schemas/ChatThinking'
        temperature:
          type: number
          description: 'Sampling temperature, controls the randomness of the output, must be a positive number within the range: `[0.0, 1.0]`. The GLM-5V-Turbo, GLM-4.6V, GLM-4.5V series default value is `0.8`, the autoglm-phone-multilingual default value is `0.0`.'
          format: float
          example: 0.8
          default: 0.8
          minimum: 0
          maximum: 1
        top_p:
          type: number
          description: 'Another method of temperature sampling, value range is: `[0.01, 1.0]`, value range is: `[0.01, 1.0]`. The GLM-5V-Turbo, GLM-4.6V, GLM-4.5V series default value is `0.6`, the autoglm-phone-multilingual default value is `0.85`.'
          format: float
          example: 0.6
          default: 0.6
          minimum: 0.01
          maximum: 1
        max_tokens:
          type: integer
          description: The maximum number of tokens for model output, the GLM-5V-Turbo supports 128K maximum output, GLM-4.6V series supports 32K maximum output, the GLM-4.5V series supports 16K maximum output, the autoglm-phone-multilingual supports 4K maximum output.
          example: 1024
          minimum: 1
          maximum: 131072
        tools:
          type: array
          description: 'A list of tools the model may call. Only support by GLM-4.6V series and autoglm-phone-multilingual. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.

            '
          items:
            anyOf:
            - $ref: '#/components/schemas/FunctionToolSchema'
        tool_choice:
          oneOf:
          - type: string
            enum:
            - auto
            description: Used to control how the model selects which function to call. This is only applicable when the tool type is function. The default value is auto, and only auto is supported.
          description: Controls how the model selects a tool.
        stop:
          type: array
          description: Stop word list. Generation stops when the model encounters any specified string. Currently, only one stop word is supported, in the format ["stop_word1"].
          items:
            type: string
          maxItems: 1
        user_id:
          type: string
          description: Unique ID for the end user, 6–128 characters. Avoid using sensitive information.
          minLength: 6
          maxLength: 128
    ChatCompletionResponseMessageToolCall:
      type: object
      properties:
        function:
          type: object
          description: Contains the function name and JSON format parameters generated by the model.
          properties:
            name:
              type: string
              description: Model-generated function name.
            arguments:
              type: object
              description: JSON format of the function call parameters generated by the model. Validate the parameters before calling the function.
          required:
          - name
          - arguments
        id:
          type: string
          description: Unique identifier for the hit function.
        type:
          type: string
          description: Tool type called by the model, currently only supports ‘function’.
    LayoutParsingRequest:
      type: object
      required:
      - model
      - file
      properties:
        model:
          type: string
          description: 'Model code: `glm-ocr`'
          example: glm-ocr
          enum:
          - glm-ocr
        file:
          type: string
          description: 'Image or PDF document to be recognized, supports URL and base64. Supported image formats: PDF, JPG, PNG. Single image ≤10MB, PDF ≤50MB, maximum support 100 pages'
          example: https://cdn.bigmodel.cn/static/logo/introduction.png
        return_crop_images:
          type: boolean
          description: Whether to return screenshot information
          default: false
        need_layout_visualization:
          type: boolean
          description: Whether to return detailed layout image result information
          default: false
        start_page_id:
          type: integer
          description: Start page number for parsing when PDF is provided
          minimum: 1
        end_page_id:
          type: integer
          description: End page number for parsing when PDF is provided
          minimum: 1
        request_id:
          type: string
          description: Unique request identifier, automatically generated if not provided
          example: req_123456789
        user_id:
          type: string
          description: 'End user ID for abuse monitoring. Length: 6-128 characters'
          minLength: 6
          maxLength: 128
          example: user_123456
    RetrievalObject:
      type: object
      properties:
        knowledge_id:
          type: string
          description: Knowledge base ID, created or obtained from the platform
        prompt_template:
          type: string
          description: 'Prompt template for requesting the model, a custom request template containing placeholders `{{ knowledge }}` and `{{ question }}`. Default template: Search for the answer to the question `{{question}}` in the document `{{ knowledge }}`. If an answer is found, respond only using statements from the document; if no answer is found, use your own knowledge to answer and inform the user that the information is not from the document. Do not repeat the question, start the answer directly.'
      required:
      - knowledge_id
    TokenizerResponse:
      type: object
      properties:
        created:
   

# --- truncated at 32 KB (85 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/zhipu-ai/refs/heads/main/openapi/zhipu-ai-paas-api-openapi.yml