A new Python wrapper called Cognocient has been developed to provide cost attribution for OpenAI and Anthropic API calls without introducing a proxy into the request path. This wrapper operates asynchronously, reporting cost data after the primary API response has been returned, ensuring that any issues with the reporting mechanism do not impact the application's performance or uptime. The tool is designed for developers who prioritize visibility into API usage costs without the dependency on a critical-path proxy, though it currently does not support streaming responses. AI
IMPACT Enables developers to track LLM API costs without adding latency or dependencies to their application's request path.
RANK_REASON The item describes a new software tool that integrates with existing LLM APIs, rather than a core AI model release or research.
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
