valuator 0.2.1

A lightweight library to fetch and search AI model pricing data

Valuator

A lightweight Python library to fetch AI model pricing data and perform searches to retrieve input and output costs per token for matching models.

Installation

pip install valuator

import asyncio
from valuator import Valuator

async def main():
    valuator = Valuator()
    try:
        await valuator.initialize()
        print(valuator.get_model_costs("claude.*haiku"))
        print(valuator.get_model_costs("gpt-4"))
    finally:
        await valuator.close()

asyncio.run(main())

Features

Fetches model pricing data from a specified URL or local cache.

Performs regex-based searches on model names for flexible matching.

Returns only input_cost_per_token and output_cost_per_token for matched models.

Optimized for low memory usage with efficient data structures (sets, cached regex).

Asynchronous HTTP requests for fast data retrieval.

Requirements

Python 3.8+

aiohttp

License MIT License