Skip to main content
POST
/
v1
/
messages
/
count_tokens
Count Tokens
curl --request POST \
  --url https://modelslab.com/api/v7/llm/v1/messages/count_tokens \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "model": "<string>",
  "messages": [
    {
      "content": "<string>"
    }
  ],
  "system": "<string>"
}
'
import requests

url = "https://modelslab.com/api/v7/llm/v1/messages/count_tokens"

payload = {
    "model": "<string>",
    "messages": [{ "content": "<string>" }],
    "system": "<string>"
}
headers = {
    "x-api-key": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)
const options = {
  method: 'POST',
  headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({model: '<string>', messages: [{content: '<string>'}], system: '<string>'})
};

fetch('https://modelslab.com/api/v7/llm/v1/messages/count_tokens', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));
<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://modelslab.com/api/v7/llm/v1/messages/count_tokens",
  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' => '<string>',
    'messages' => [
        [
                'content' => '<string>'
        ]
    ],
    'system' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-api-key: <api-key>"
  ],
]);

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

curl_close($curl);

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

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

func main() {

	url := "https://modelslab.com/api/v7/llm/v1/messages/count_tokens"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\"\n    }\n  ],\n  \"system\": \"<string>\"\n}")

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

	req.Header.Add("x-api-key", "<api-key>")
	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))

}
HttpResponse<String> response = Unirest.post("https://modelslab.com/api/v7/llm/v1/messages/count_tokens")
  .header("x-api-key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\"\n    }\n  ],\n  \"system\": \"<string>\"\n}")
  .asString();
require 'uri'
require 'net/http'

url = URI("https://modelslab.com/api/v7/llm/v1/messages/count_tokens")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\"\n    }\n  ],\n  \"system\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body
{
  "input_tokens": 123
}

Request

POST https://modelslab.com/api/v7/llm/v1/messages/count_tokens
curl -X POST https://modelslab.com/api/v7/llm/v1/messages/count_tokens \
  -H "x-api-key: $MODELSLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "Qwen/Qwen2.5-VL-72B-Instruct-together",
    "messages": [
      {"role": "user", "content": "What is the capital of France?"}
    ]
  }'

Body

{
  "model": "Qwen/Qwen2.5-VL-72B-Instruct-together",
  "messages": [
    {"role": "user", "content": "What is the capital of France?"}
  ],
  "system": "You are a helpful assistant."
}

Response

{
  "input_tokens": 15
}

Use Cases

  • Cost estimation: Calculate the cost of a request before sending it
  • Context window management: Ensure your messages fit within the model’s context window
  • Token budgeting: Allocate token budgets across multiple requests

Example

from anthropic import Anthropic

client = Anthropic(
    api_key="YOUR_MODELSLAB_API_KEY",
    base_url="https://modelslab.com/api/v7/llm",
)

# Count tokens before sending
token_count = client.messages.count_tokens(
    model="Qwen/Qwen2.5-VL-72B-Instruct-together",
    messages=[
        {"role": "user", "content": "Write a detailed essay about AI"}
    ],
)

print(f"Input tokens: {token_count.input_tokens}")

Authorizations

x-api-key
string
header
required

API key authentication via x-api-key header

Headers

anthropic-version
string
default:2023-06-01

Anthropic API version

Body

application/json
model
string
required

Model ID to count tokens for

messages
object[]
required

Messages to count tokens for

system
string

System prompt to include in token count

Response

200 - application/json

Token count response

input_tokens
integer

Number of input tokens