Metadata-Version: 2.4
Name: valuator
Version: 0.2.0
Summary: A lightweight library to fetch and search AI model pricing data
Author: Vikas Konaparthi
Author-email: vikaskonaparthi@gmail.com
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: aiohttp>=3.8.0
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

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

Usage
import asyncio
from valuator import Valuator

async def main():
    valuator = Valuator()
    try:
        # Search with regex pattern
        costs = valuator.get_model_costs("claude.*haiku")
        print(costs)

        # Search with partial name
        costs = valuator.get_model_costs("gpt-4")
        print(costs)
    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
