Count message tokens

POST/messages/count_tokens

Estimates how many input tokens a Messages request would use, without running it: free, even at zero credit, and no operator is called. It is an estimate — one token for every 4 characters of the system prompt, the messages and the tool schemas — because each model has its own tokenizer; what a real call costs is the usage its operator reports.

Catalogue checked on 20 Oct 2026

SoonOpening soon: what follows describes the service as it will work.

Server URLhttps://evanesca.app/api/v1

POST/messages/count_tokensOpens at launch

AuthorizationBearer $EVANESCA_API_KEY

Headers

x-api-keystringrequired
Your key, which starts with sk-eva-. Authorization: Bearer followed by the key works too: that is where Claude Code sends it when ANTHROPIC_AUTH_TOKEN is set.
anthropic-versionstring
Sent by Anthropic's SDKs; accepted, and has no effect here.
Content-Typestringrequired
application/json: the body is JSON.

Request body

application/json

modelstringrequired
Required by the format; the estimate does not depend on it.
messagesarrayrequired
The turns, as for POST /messages.
system, toolsstring | array · array
Counted as well when you send them.

Where it runs, what it costs

Evanesca · on the record

Answered by: Evanesca itself: no model runs, no operator is called.
Costs: Nothing: a valid key is enough, even with no credit left.
Precision: An estimate at 4 characters per token, never a billed amount. Long inline data, such as a base64 image, is left out of the count.

Errors

Status	type	Meaning
400	`invalid_request`	The body is not valid JSON, or model or messages is missing.
401	`invalid_api_key`	No key, a malformed key, or a revoked one.

Other operator errors reach you with its status and body, and Retry-After when it sends one (errors).

curl https://evanesca.app/api/v1/messages/count_tokens \
  -H "x-api-key: $EVANESCA_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-4-26b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

import os
import anthropic

client = anthropic.Anthropic(
    base_url="https://evanesca.app/api",
    api_key=os.environ["EVANESCA_API_KEY"],
)

count = client.messages.count_tokens(
    model="gemma-4-26b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(count.input_tokens)

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

const client = new Anthropic({
  baseURL: "https://evanesca.app/api",
  apiKey: process.env.EVANESCA_API_KEY,
});

const count = await client.messages.countTokens({
  model: "gemma-4-26b",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(count.input_tokens);

package main

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

func main() {
	body := strings.NewReader(`{"model":"gemma-4-26b","messages":[{"role":"user","content":"Hello"}]}`)
	req, err := http.NewRequest("POST", "https://evanesca.app/api/v1/messages/count_tokens", body)
	if err != nil {
		panic(err)
	}
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVANESCA_API_KEY"))
	req.Header.Set("Content-Type", "application/json")
	res, err := http.DefaultClient.Do(req)
	if err != nil {
		panic(err)
	}
	defer res.Body.Close()
	out, _ := io.ReadAll(res.Body)
	fmt.Println(res.Status, string(out))
}

{
  "input_tokens": 10
}

{
  "type": "error",
  "error": {
    "type": "invalid_api_key",
    "message": "Invalid or missing API key."
  }
}