Count Tokens

Estimate how many input tokens an Anthropic Messages request would consume. No upstream inference is invoked, no charge is incurred, and it does not count against concurrency, but the API key validity and the account's balance / subscription status are still checked.

Protocol boundary

This is the Anthropic-style token counting endpoint. The request body matches /v1/messages. Anthropic-platform groups forward token counting upstream, OpenAI-platform groups use compatible counting, and Grok returns an estimate.

Endpoint

POST https://api.sakrylle.com/v1/messages/count_tokens

Headers

Name	Required	Description
Authorization	Yes	Bearer sk-xxxxxxxxxxxxxxxx
Content-Type	Yes	application/json
anthropic-version	No	e.g. 2023-06-01, matches Anthropic's official header

Request body

The request body is identical to POST /v1/messages:

Field	Type	Required	Description
model	string	Yes	Claude model ID, e.g. claude-haiku-4-5-20251001
messages	array	Yes	Full conversation message list
system	string | array	No	System prompt
tools	array	No	Tool definitions; tokens for these are included in the count
tool_choice	object	No	Same as messages

Inference-only fields (temperature, top_p, stream, max_tokens, etc.) are accepted for parsing but do not affect the token count.

Example request

{
  "model": "claude-haiku-4-5-20251001",
  "system": "You are a concise assistant.",
  "messages": [
    { "role": "user", "content": "Introduce yourself." }
  ]
}

Example response

{
  "input_tokens": 36
}

The field name matches Anthropic's /v1/messages/count_tokens. The gateway forwards the upstream account's response.

Errors

• 400 invalid_request_error — missing model, body is not JSON, or parse failure
• 401 authentication_error — invalid API key
• 403 billing_error — balance or subscription quota exhausted (still validated even though no charge applies)
• 503 api_error — no upstream account is available

For the full table, see Errors.

Code samples

curl

curl https://api.sakrylle.com/v1/messages/count_tokens \
  -H "Authorization: Bearer sk-xxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-haiku-4-5-20251001",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Python

from anthropic import Anthropic

client = Anthropic(
    api_key="sk-xxxxxxxxxxxxxxxx",
    base_url="https://api.sakrylle.com",
)

resp = client.messages.count_tokens(
    model="claude-haiku-4-5-20251001",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.input_tokens)

Node

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: "sk-xxxxxxxxxxxxxxxx",
  baseURL: "https://api.sakrylle.com",
});

const resp = await client.messages.countTokens({
  model: "claude-haiku-4-5-20251001",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(resp.input_tokens);

Go

package main

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

func main() {
    body := []byte(`{
      "model": "claude-haiku-4-5-20251001",
      "messages": [{"role":"user","content":"Hello"}]
    }`)
    req, _ := http.NewRequest("POST",
        "https://api.sakrylle.com/v1/messages/count_tokens",
        bytes.NewReader(body))
    req.Header.Set("Authorization", "Bearer sk-xxxxxxxxxxxxxxxx")
    req.Header.Set("Content-Type", "application/json")
    req.Header.Set("anthropic-version", "2023-06-01")
    resp, err := http.DefaultClient.Do(req)
    if err != nil {
        panic(err)
    }
    defer resp.Body.Close()
    out, _ := io.ReadAll(resp.Body)
    fmt.Println(string(out))
}

Rust

use reqwest::Client;
use serde_json::json;

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    let client = Client::new();
    let resp: serde_json::Value = client
        .post("https://api.sakrylle.com/v1/messages/count_tokens")
        .bearer_auth("sk-xxxxxxxxxxxxxxxx")
        .header("anthropic-version", "2023-06-01")
        .json(&json!({
            "model": "claude-haiku-4-5-20251001",
            "messages": [{"role": "user", "content": "Hello"}]
        }))
        .send()
        .await?
        .json()
        .await?;
    println!("{resp:#}");
    Ok(())
}

Java

import java.net.URI;
import java.net.http.*;

public class CountTokens {
  public static void main(String[] args) throws Exception {
    String body = """
      {"model":"claude-haiku-4-5-20251001",
       "messages":[{"role":"user","content":"Hello"}]}
      """;
    HttpRequest req = HttpRequest.newBuilder()
      .uri(URI.create("https://api.sakrylle.com/v1/messages/count_tokens"))
      .header("Authorization", "Bearer sk-xxxxxxxxxxxxxxxx")
      .header("Content-Type", "application/json")
      .header("anthropic-version", "2023-06-01")
      .POST(HttpRequest.BodyPublishers.ofString(body))
      .build();
    HttpResponse<String> resp = HttpClient.newHttpClient()
      .send(req, HttpResponse.BodyHandlers.ofString());
    System.out.println(resp.body());
  }
}

C#

using System.Net.Http.Headers;
using System.Text;

var http = new HttpClient();
http.DefaultRequestHeaders.Authorization =
    new AuthenticationHeaderValue("Bearer", "sk-xxxxxxxxxxxxxxxx");
http.DefaultRequestHeaders.Add("anthropic-version", "2023-06-01");

var payload = """
  {"model":"claude-haiku-4-5-20251001",
   "messages":[{"role":"user","content":"Hello"}]}
  """;
var resp = await http.PostAsync(
    "https://api.sakrylle.com/v1/messages/count_tokens",
    new StringContent(payload, Encoding.UTF8, "application/json"));
Console.WriteLine(await resp.Content.ReadAsStringAsync());