LLM deployment planner: given a model and a GPU, answers will it fit, will it hit your SLO, and what will it cost. Sizes VRAM and KV-cache from the model's real architecture, and labels every number measured, estimated, or unknown.
Enables AI agents and MCP clients to estimate VRAM footprint and tensor parallelization requirements for quantized llama.cpp models, returning structured outputs without external dependencies.
Deterministic AI data-center design engine exposed as MCP tools for sizing, validation, and physical layout. Supports NVIDIA Hopper, Blackwell, and Vera Rubin with anonymous access to the remote engine.
Enables AI cost calculation, comparison, and optimization across major providers like Anthropic, OpenAI, Google, Meta, and Mistral. Supports cost estimation, budget-aware model finding, and token estimation through a simple API and MCP integration.
