Free API cost calculators – know your bill before it arrives
12 free calculators running in-browser when provider pricing pages already exist.

VRAM calculator with crowd-sourced tok/s benchmarks when model cards already exist.
Local LLM hobbyists and developers running models on consumer GPUs
llama.cpp model cards · Hugging Face model pages · Various GPU compatibility checkers
12 free calculators running in-browser when provider pricing pages already exist.
Yet another token calculator when OpenAI and dozens of others already exist.
Opinionated llama.cpp VRAM calculator that outputs ready-to-run server commands.
Single lookup table: cheapest way to run any model across APIs, GPUs, or cloud.
SQLite-based LLM inference hitting 210MB RSS beats OS paging with deterministic memory control.
LLM cost calculator with current pricing, but spreadsheets and existing tools already do this.