Tokenizer

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.

POST /paas/v4/tokenizer

Text Tokenizer

cURL

curl --request POST \
  --url https://api.z.ai/api/paas/v4/tokenizer \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "glm-4.6",
  "messages": [
    {
      "role": "user",
      "content": "What opportunities and challenges will the Chinese large model industry face in 2025?"
    }
  ]
}
'

200

{
  "id": "20241120141244890ab4ee4af84acf",
  "usage": {
    "prompt_tokens": 123,
    "image_tokens": 123,
    "video_tokens": 123,
    "total_tokens": 123
  },
  "created": 1727156815,
  "request_id": "1"
}

Authorizations

Authorization · string · header · required

Use the following format for authentication: Bearer

Body

application/json

model · enum<string> · default: glm-4.6 · required

The model code to be called.

Available options: glm-4.6, glm-4.6v, glm-4.5

Example:

"glm-4.6"

messages · (User Message · object | System Message · object | Assistant Message · object)[] · required

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.

Minimum array length: 1

User Message

System Message

Assistant Message

Hide child attributes

messages. role · enum<string> · default: user · required

Role of the message author

Available options: user

messages. content · (Text · object | Image · object | Video · object | File · object)[] string · required

Multimodal message content, supports text, images, video, file

Text

Image

Video

File

Hide child attributes

messages.content. type · enum<string> · default: text · required

Content type is text

Available options: text

messages.content. text · string · required

Text content

tools · Function Call · object[]

List of tools the model can call. Supports up to 128 functions.

Hide child attributes

tools. type · enum<string> · default: function · required

Available options: function

tools. function · object · required

Hide child attributes

tools.function. name · string · required

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.

Required string length: 1 - 64

Pattern: ^[a-zA-Z0-9_-]+$

tools.function. description · string · required

A description of what the function does, used by the model to choose when and how to call the function.

tools.function. parameters · object · required

Parameters defined using JSON Schema. Must pass a JSON Schema object to accurately define accepted parameters. Omit if no parameters are needed when calling the function.

request_id · string

Passed by the user side, needs to be unique; used to distinguish each request, 6–64 characters. If not provided by the user side, the platform will generate one by default.

Required string length: 6 - 64

user_id · string

Unique ID for the end user, 6–128 characters. Avoid using sensitive information.

Required string length: 6 - 128

Response

200

application/json

Business processing successful

id · string · required

The task sequence number generated by the Zhipu AI Open Platform. Please use this number when calling the request result interface.

Example:

"20241120141244890ab4ee4af84acf"

usage · object · required

Hide child attributes

usage. prompt_tokens · number

Prompt tokens in this input

usage. image_tokens · number

Image tokens in this input

usage. video_tokens · number

Video tokens in this input

usage. total_tokens · number

Total tokens in this input

created · integer<int64>

Example:

1727156815

request_id · string

The task number submitted by the client or generated by the platform when the request was initiated.

Example:

"1"