> ## Documentation Index > Fetch the complete documentation index at: https://docs.llumo.ai/llms.txt > Use this file to discover all available pages before exploring further. # Quickstart > Reduce LLM cost and gain 360° insights of your LLM outputs. ## Reduce Cost LLUMO compresses your tokens to build production ready AI at 50% cost and 10x speed. Compress your prompt by 70% before passing to LLMs. Connect to LLUMO API and reduce cost by 50%. Save cost in OpenAI API calls using LLUMO compressor API. Save cost in Google Vertex pipeline using LLUMO compressor API. Save cost in Langchain pipeline using LLUMO compressor API. Save cost in Llama Index pipeline using LLUMO compressor API. ## Evaluate LLMs The only customizable LLMs evaluation tool to gain 360° insights into your AI output quality. Evaluate & compare all universal language models at one place. Use LLUMO AI’s proprietary technology to evaluate output from OpenAI GPT models. Use LLUMO AI's proprietary technology to evaluate LLM output and gain insights. Use LLUMO AI’s proprietary technology to evaluate output from Google Gemini models.