TokenCost is an open-source developer utility designed to estimate the cost of using large language model APIs by calculating token usage and translating it into real monetary values. The tool focuses on helping developers understand how much their prompts and generated completions cost when interacting with commercial AI models. It works by counting tokens in prompts and responses before or after sending requests and then applying pricing information associated with different models. This allows engineers building AI applications, chatbots, or autonomous agents to monitor and predict API expenses during development and production. The library includes pricing information for hundreds of language models and is frequently updated to reflect pricing changes from major AI providers.
Features
- Token counting for prompts and generated completions
- Automatic conversion of token usage into estimated USD cost
- Price tracking for hundreds of large language model APIs
- Simple integration into Python-based AI applications
- Support for cost monitoring during prompt and completion generation
- Utility functions for calculating total API usage cost