文本分词器

Tokenizer 用于将文本切分为模型可识别的 token 并计算数量。它接收用户输入的文本，通过模型进行分词处理，最终返回对应的 token 数量。适用于文本长度评估、模型输入预估、对话上下文截断、费用计算等。点击 Try it 按钮可快速试用。

POST /paas/v4/tokenizer

文本分词器

cURL

curl --request POST \
  --url https://open.bigmodel.cn/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?"
    }
  ]
}
'

import requests

url = "https://open.bigmodel.cn/api/paas/v4/tokenizer"

payload = {
    "model": "glm-4.6",
    "messages": [
        {
            "role": "user",
            "content": "What opportunities and challenges will the Chinese large model industry face in 2025?"
        }
    ]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'glm-4.6',
    messages: [
      {
        role: 'user',
        content: 'What opportunities and challenges will the Chinese large model industry face in 2025?'
      }
    ]
  })
};

fetch('https://open.bigmodel.cn/api/paas/v4/tokenizer', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

HttpResponse<String> response = Unirest.post("https://open.bigmodel.cn/api/paas/v4/tokenizer")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"glm-4.6\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"What opportunities and challenges will the Chinese large model industry face in 2025?\"\n    }\n  ]\n}")
  .asString();

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://open.bigmodel.cn/api/paas/v4/tokenizer"

	payload := strings.NewReader("{\n  \"model\": \"glm-4.6\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"What opportunities and challenges will the Chinese large model industry face in 2025?\"\n    }\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://open.bigmodel.cn/api/paas/v4/tokenizer",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => 'glm-4.6',
    'messages' => [
        [
                'role' => 'user',
                'content' => 'What opportunities and challenges will the Chinese large model industry face in 2025?'
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

200

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

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

Authorizations

Authorization · string · header · required

标准的 HTTP Bearer 认证方式，在 API Keys 页面获取密钥。

Body

application/json

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

调用的模型代码。

Available options: glm-4.6, glm-4.6v, glm-4.5, glm-4.5-air, glm-4-0520, glm-4-long, glm-4-air, glm-4-flash

Example:

"glm-4.6v"

messages · (用户消息 · object | 系统消息 · object | 助手消息 · object)[] · required

对话消息列表，包含当前对话的完整上下文信息。每条消息都有特定的角色和内容，模型会根据这些消息生成回复。消息按时间顺序排列，支持角色：system（系统消息，用于设定AI的行为和角色）、user（用户消息，来自用户的输入）、assistant（助手消息，来自AI的回复）。视觉模型支持纯文本和多模态内容（文本、图片、视频、文件）。注意不能只包含系统或助手消息。

Minimum array length: 1

用户消息

系统消息

助手消息

Show child attributes

tools · Function Call · object[]

模型可以调用的工具列表。支持函数调用、知识库检索和网络搜索。使用此参数提供模型可以生成 JSON 输入的函数列表或配置其他工具。最多支持 128 个函数。目前 GLM-4 系列已支持所有 tools，GLM-4.5 已支持 web search 和 retrieval。

Show child attributes

request_id · string

请求唯一标识符。由用户端传递，ID长度要求：最少6个字符，最多64个字符，建议使用UUID格式确保唯一性，若未提供平台将自动生成。

Required string length: 6 - 64

user_id · string

终端用户的唯一ID

Response

200

application/json

业务处理成功

id · string · required

智谱开放平台生成的任务序号，调用请求结果接口时请使用此序号。

Example:

"20241120141244890ab4ee4af84acf"

usage · object · required

Show child attributes

created · integer<int64>

Example:

1727156815

request_id · string

请求发起时客户端提交的任务号或平台生成的任务号。

Example:

"1"