Estimate Input Tokens

Send the x-api-key: <API Key>, anthropic-version: 2023-06-01, and Content-Type: application/json headers.

Production HTTP requests use https://api.mosi.cn. Before running the examples below, set MOSS_API_ORIGIN to https://api.mosi.cn and MOSS_API_KEY to your MOSS API Key.

Request parameters

FieldTypeUsageDescription

model: stringRequired

Use nex-n2.6.

messages: array<object>Required

Pass the text-only user messages to estimate.

messages[].role: stringRequired

For a text-only user message, set this field to user.

messages[].content: stringRequired

Text to estimate.

Response fields

FieldTypeDescription

input_tokens: integer

Estimated input token count for this request.

Error handling and compatibility

Call the counting endpoint with the same model and the messages you plan to send. Once you have input_tokens, you can use it to reserve output room for the subsequent generation, or to trim the history first when the input is too long. For the actual generation, record usage from the usage returned by Messages.

Platform error codes

Request example

curl -X POST "$MOSS_API_ORIGIN/v1/messages/count_tokens" \
  -H 'Content-Type: application/json' \
  -H "x-api-key: $MOSS_API_KEY" \
  -H 'anthropic-version: 2023-06-01' \
  -d '{
  "model": "nex-n2.6",
  "messages": [
    {
      "role": "user",
      "content": "Reply with only the result of 17 × 23."
    }
  ]
}'

import os
import requests

url = os.environ["MOSS_API_ORIGIN"].rstrip("/") + "/v1/messages/count_tokens"
headers = {
    "Content-Type": 'application/json',
    "x-api-key": os.environ["MOSS_API_KEY"],
    "anthropic-version": '2023-06-01',
}

payload = {'model': 'nex-n2.6', 'messages': [{'role': 'user', 'content': 'Reply with only the result of 17 × 23.'}]}

response = requests.post(url, headers=headers, json=payload, timeout=(10, 120))
response.raise_for_status()
print(response.text)

async function main() {
  const origin = process.env.MOSS_API_ORIGIN;
  if (!origin) throw new Error("Set MOSS_API_ORIGIN");
  const url = origin.replace(/\/+$/, "") + "/v1/messages/count_tokens";
  const apiKey = process.env.MOSS_API_KEY;
  if (!apiKey) throw new Error("Set MOSS_API_KEY");
  const headers: Record<string, string> = {
    "Content-Type": "application/json",
    "x-api-key": apiKey,
    "anthropic-version": "2023-06-01",
  };

  const payload = {
    "model": "nex-n2.6",
    "messages": [
      {
        "role": "user",
        "content": "Reply with only the result of 17 × 23."
      }
    ]
  };

  const response = await fetch(url, {
    method: "POST",
    headers,
    body: JSON.stringify(payload),
  });
  if (!response.ok) {
    throw new Error("HTTP " + response.status + ": " + await response.text());
  }
  console.log(await response.text());
}

main().catch((error: unknown) => {
  console.error(error);
  process.exitCode = 1;
});

Response example

The text request example on this page returned 22 input tokens during production testing. Estimates for other requests depend on the input.

{
  "input_tokens": 22
}

Request parameters

Response fields

Error handling and compatibility

Related documentation