Categories › AI & Agents › Models, LLM APIs, routing, serving, training & GPUs
Real cost per AI result, LLM prices, switch costs, shutdown dates, A/B test sizes and judge checks.
Remote server: your requests and data go to aiappsthatwork.com. Claude Code: claude mcp add --transport http ai-apps-that-work-free-tools https://aiappsthatwork.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
real_cost_per_result — Prices the AI steps behind one request from current list prices (LLM tokens, images, video seconds or a fixed amount) and returns the cost pmodel_switch_cost — Compares two priced LLMs on six common task shapes (support answer, invoice extraction, lead scoring, email draft, translation, search re-ramodel_prices — Looks up list prices for LLMs (USD per million input, output and cached input tokens, and context size), image models (USD per image by qualmodel_shutdowns — Lists announced API shutdown dates for AI models from OpenAI, Anthropic, Google and other providers, with days left, the suggested replacemeab_test_sample_size — Returns how many results each version of a prompt or model needs before a difference in how often results work first time is statistically rjudge_agreement — Compares a person's verdicts with an AI judge's verdicts on the same results. Returns the agreement rate, Cohen's kappa with confidence intebuild_judge_prompt — Builds a pass/fail LLM-as-a-judge prompt for one kind of AI step (make, answer, transform, extract, judge, find, predict, plan, act or learnlaunch_checklist — The 20 AI-specific launch checks for an AI app (spending caps, rate limits, server-side keys, credit charging, version tags, records of whicNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.