Skip to main content
MCP server CX Codex

//beforeyouship — Claude Code MCP server: LLM cost modeling

//beforeyouship — LLM cost modeling from your editor is an MCP server for Claude Code that estimates an LLM app’s monthly cost using architecture presets, token prices and three cost scenarios.

no license 169 installs updated 2026-06-11

Install into Claude Code · Platform CLI: remote server All methods and platforms ↓
claude mcp add --transport http cost-model https://cost-model--beforeyouship.run.tools
Open on GitHub

What //beforeyouship — LLM cost modeling from your editor does

Three tools land in your editor. list_archetypes hands back seven preset LLM architectures (chatbot, RAG pipeline, multi-step agent and others), each with default usage numbers. get_model_prices lists per-1M-token rates for input, output, cached input and batch, along with context windows and a note on how stale the pricing is. estimate_cost takes an archetype id plus calls_per_day and returns a monthly figure.

The model behind it accounts for retried calls, prompt caching, batch discounts, infra overhead and 3×/10× traffic growth. You get Naive, Realistic and Worst Case dollars per month for each model, growth scenarios, and a recommended pick. Token counts and multipliers can be overridden.

No key is needed to start: demo mode covers six free-tier models. A Pro key from beforeyouship.dev opens the 18-model catalog, so without it you compare across six models only — thin ground when the shortlist is GPT-5.x, Claude, Gemini and DeepSeek. Point your client at https://cost-model--beforeyouship.run.tools.

What it helps with

  • model the monthly bill for an LLM app before writing code
  • compare Claude, Gemini and GPT-5.x on your own traffic profile
  • see what 3× and 10× growth does to the cost
  • pull current per-1M-token rates including cached and batch pricing
  • start from a preset RAG or agent archetype instead of a blank estimate

Example prompts for the agent

  • List the archetypes and estimate what a multi-step agent costs per month.
  • Run estimate_cost for a chatbot on my traffic and compare Claude against Gemini.
  • Pull get_model_prices and flag any pricing that has gone stale.

How to install //beforeyouship — LLM cost modeling from your editor

Platform CLI: remote server

claude mcp add --transport http cost-model https://cost-model--beforeyouship.run.tools

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about //beforeyouship — LLM cost modeling from your editor

How do I install //beforeyouship in Claude Code?

Run claude mcp add --transport http cost-model https://cost-model--beforeyouship.run.tools and the server is registered for your sessions.

What does //beforeyouship do?

It estimates the real monthly bill for an LLM architecture, returning three cost scenarios plus a model recommendation.

Do I need an API key?

Not to start. Demo mode runs keyless over six free-tier models; a Pro key from beforeyouship.dev unlocks the full 18-model catalog.

Similar MCP servers

All MCP servers for AI and ML →

Project sponsors

Companies that keep this analytics open