Your friendly token counting pal for OpenAI, Anthropic, and Google LLM models. Simple, accurate, fast.
Project description
token-count
A simple, practical Python package for counting tokens across OpenAI, Anthropic, and Google (Gemini) models using their official tokenizers and APIs.
Features
- OpenAI: Local, offline token counting via
tiktoken(official tokenizer) - Anthropic: Official
messages.count_tokensAPI - Google (Gemini): Official
models.countTokensviagoogle-genaiSDK - Provider-agnostic message format
- Robust model name handling with fallbacks
- Optional dependencies for each provider
Installation
# Basic installation (OpenAI support only)
pip install token-count
# With Anthropic support
pip install 'token-count[anthropic]'
# With Google support
pip install 'token-count[google]'
# With all providers
pip install 'token-count[anthropic,google]'
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
tokenpal-0.1.0.tar.gz
(5.7 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file tokenpal-0.1.0.tar.gz.
File metadata
- Download URL: tokenpal-0.1.0.tar.gz
- Upload date:
- Size: 5.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.11.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4a3beabcec232ebb6b1ab22b322b92dba0768bb8ffc4c5b001ca87df1f4785b0
|
|
| MD5 |
1febfc32680a701078570f72a70214f5
|
|
| BLAKE2b-256 |
4c57fc9ffdaf98ebc5b26e9320e72d0fabf2997cf8a60eb0861daca645b45ec0
|
File details
Details for the file tokenpal-0.1.0-py3-none-any.whl.
File metadata
- Download URL: tokenpal-0.1.0-py3-none-any.whl
- Upload date:
- Size: 5.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.11.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b445352706d30524a21df38a1785803a90a3b98a7ca171d9019603b605a72cde
|
|
| MD5 |
6ab2bd0707aa6702981aeb6e20ca83fd
|
|
| BLAKE2b-256 |
79333b6bae36ddc6f841ca2a878360db68879ca0891a29e031d5246fb81f0085
|
