{"name":"How Much to Run AI","slug":"how-much-to-run-ai","canonical_url":"https://indiestore.co/product/how-much-to-run-ai","website":"https://howmuchtorunai.com/","tagline":"Calculate the true cost of self-hosting LLMs.","description":"Stop guessing your AI infrastructure budget—calculate the exact VRAM, hardware, and electricity costs for any open-weight model in seconds.","overview":"How Much to Run AI is a specialized financial planning tool for AI infrastructure. It helps engineering teams move beyond 'free weights' by calculating the true total cost of ownership (TCO) for deploying models like DeepSeek, Qwen, and Llama. The platform breaks down complex variables including VRAM requirements, hardware depreciation, PUE (cooling overhead), and FTE labor shares to provide a realistic monthly budget for self-hosted inference.","category":"AI","audience":"AI Engineers, CTOs, and DevOps teams evaluating build-vs-buy decisions for LLM deployment.","founder":"January Jung","questions":[{"question":"How is the VRAM requirement calculated?","answer":"VRAM is estimated using the formula: params × bytes/param × runtime headroom (default 1.2x). For MoE models, it budgets for all expert weights."},{"question":"Does the calculator include cloud rental prices?","answer":"Yes, it includes pay-as-you-go hourly rates from AWS, Google Cloud, and Microsoft Azure, which already factor in electricity costs."},{"question":"Can I adjust the labor costs?","answer":"Yes, you can customize the monthly salary range for AI operations engineers and the FTE share required for your specific deployment."}],"sources":{"text":"https://indiestore.co/product/how-much-to-run-ai/llms.txt","json":"https://indiestore.co/product/how-much-to-run-ai/data.json"},"source_note":"Public product information listed on IndieStore. Listing is not an endorsement. Confirm current pricing and availability on the official website; missing information is unknown."}