# Count LLM Tokens & Estimate Cost - GPT, Claude, Gemini (`tidybytetools/llm-token-counter`) Actor

Count tokens and estimate cost for GPT, Claude and Gemini. Offline. Exact OpenAI counts via tiktoken; Claude/Gemini marked as estimates. $0.0005 per unique text. Works from Apify MCP and the API.

- **URL**: https://apify.com/tidybytetools/llm-token-counter.md
- **Developed by:** [Tidy Byte Tools](https://apify.com/tidybytetools) (community)
- **Security:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $0.50 / 1,000 text counteds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## LLM Token Counter & Cost Estimator - GPT, Claude, Gemini

Count tokens for GPT, Claude, Gemini and more, and estimate cost from public list prices. Offline, no API key. $0.0005 per text, all selected models included.

### Website and local versions

- **[Website](https://tidybytetools.github.io/)** — Tidy Byte Tools product page

### What it does

- Counts tokens for each text you paste, list, or load from a file.
- You can pick more than one model. You still pay once per text.
- OpenAI counts (GPT and o3) use the real tiktoken rules and are exact.
- Claude and Gemini counts are close estimates. Each result is marked exact or estimate.
- Estimates input and output cost from public list prices (dated 9 Nov 2026, America/Chicago). Prices can change.
- Gives a short summary of totals.

### Price

You pay **$0.0005** per unique text counted. Every model you pick is included in that price. Blank lines and repeats are free. There is no start fee from us. Apify adds its normal small platform cost.
Set a max cost for the run and we stop there. We never charge for work we did not save.

### How to use

1. Paste text, add a list, or add file links.
2. Pick the models you care about.
3. Click **Start**.
4. Get results in the **Output** tab.

### Input

- **Texts**: One text per line.
- **Or paste text**: Paste one text, or many if you split by line.
- **File links**: Links to text files. Each file is one text, unless you split by line.
- **How to split paste and files**: Keep as one text, split on every line, or split on blank lines.
- **Models**: The models to count. OpenAI is exact. Claude and Gemini are estimates.

### Good to know

- No API key is needed. Nothing is sent to OpenAI, Anthropic or Google.
- Cost figures use public list prices as of 9 Nov 2026 (America/Chicago). They are a guide, not a bill from the model maker.
- Claude and Gemini token counts can be a little high or a little low.
- Files up to 50 MB each.
- Your data is only used for your run.
- Made by Tidy Byte Tools. Questions? Open an issue on this Actor's page.

### More tools from Tidy Byte Tools

These Actors work well together:

- [PDF Table Extractor](https://apify.com/tidybytetools/pdf-table-pull) — PDF tables to CSV, Excel and JSON. $0.003 per page with a table.
- [PDF, Word and Web Page to Markdown](https://apify.com/tidybytetools/doc-to-markdown) — Clean Markdown and RAG chunks. $0.003 per file.
- [HTML Table Extractor](https://apify.com/tidybytetools/html-table-extractor) — Web tables to CSV and JSON. $0.0005 per data row.
- [Broken Link Checker](https://apify.com/tidybytetools/broken-link-checker) — Check site and sitemap links. $0.001 per link.
- [Markdown Chunker for RAG](https://apify.com/tidybytetools/markdown-rag-chunker) — Split Markdown by headings. $0.0001 per chunk.
- [CSV and Excel Data Cleaner](https://apify.com/tidybytetools/csv-excel-data-cleaner) — Dedupe and fix dates, emails and phones. $0.0005 per clean row.
- [JSON to CSV Converter](https://apify.com/tidybytetools/json-to-csv-flattener) — Flatten nested JSON for spreadsheets. $0.0001 per row.
- [CSV Encoding Fixer and Splitter](https://apify.com/tidybytetools/csv-encoding-fixer-splitter) — Fix garbled letters like é and split big files. $0.01 per file.
- [Phone Number Validator](https://apify.com/tidybytetools/phone-number-validator-formatter) — Check and format numbers offline. $0.001 per number.
- [LLM Token Counter](https://apify.com/tidybytetools/llm-token-counter) — Offline token and cost estimates for GPT, Claude and Gemini. $0.0005 per unique text.

Free local tools (no Apify account needed): [pdf-table-pull-lite](https://github.com/tidybytetools/pdf-table-pull-lite), [doc2md-lite](https://github.com/tidybytetools/doc2md-lite), [link-check-lite](https://github.com/tidybytetools/link-check-lite), [md-chunk-lite](https://github.com/tidybytetools/md-chunk-lite), [json-shaper-lite](https://github.com/tidybytetools/json-shaper-lite).

Website: <https://tidybytetools.github.io>. All Actors: [apify.com/tidybytetools](https://apify.com/tidybytetools).

### Agent tip

Count tokens and estimate cost for GPT, Claude and Gemini. Offline. Exact OpenAI counts via tiktoken; Claude/Gemini marked as estimates. $0.0005 per unique text. Works from Apify MCP and the API.

# Actor input Schema

## `texts` (type: `array`):

One text per line. Each line is counted on its own.

## `text` (type: `string`):

Paste one text, or many texts if you split by line below.

## `fileUrls` (type: `array`):

Links to .txt, .md, .json, .csv or other text files. Each file is one text, unless you split by line.

## `splitMode` (type: `string`):

Lists in the Texts box are always one text per line.

## `models` (type: `array`):

OpenAI counts are exact (tiktoken). Claude and Gemini counts are close estimates, marked in the results.

## Actor input object example

```json
{
  "texts": [
    "Hello, how many tokens is this?",
    "A longer sample: the quick brown fox jumps over the lazy dog."
  ],
  "splitMode": "whole",
  "models": [
    "gpt-4o",
    "gpt-5-mini",
    "claude-sonnet-5.5"
  ]
}
```

# Actor output Schema

## `results` (type: `string`):

No description

## `summary` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "texts": [
        "Hello, how many tokens is this?",
        "A longer sample: the quick brown fox jumps over the lazy dog."
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("tidybytetools/llm-token-counter").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "texts": [
        "Hello, how many tokens is this?",
        "A longer sample: the quick brown fox jumps over the lazy dog.",
    ] }

# Run the Actor and wait for it to finish
run = client.actor("tidybytetools/llm-token-counter").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "texts": [
    "Hello, how many tokens is this?",
    "A longer sample: the quick brown fox jumps over the lazy dog."
  ]
}' |
apify call tidybytetools/llm-token-counter --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,tidybytetools/llm-token-counter"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/EAdyLwq4QPad7v3NJ/builds/bxYiIUpwi1260Y8kD/openapi.json