//beforeyouship — LLM cost modeling from your editor
Rank #118,576smithery/beforeyouship/cost-model
Model the realistic monthly cost of an LLM app **before you build it**. Not a token calculator: retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth are modeled in, across GPT-5.x, Claude, Gemini, DeepSeek, and more. **Works without a key.** Connect and ask — demo mode covers the six free-tier models. A Pro API key ([beforeyouship.dev](https://beforeyouship.dev)) unlocks the full 18-model catalog. ## Tools | Tool | What it does | |---|---| - **`estimate_cost`** Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case $/mo per model, growth scenarios, and an opinionated recommendation. | - **`get_model_prices`** Current per-1M-token pricing (input, output, cached, batch) with context windows and staleness metadata. | - **`list_archetypes`** Seven preset architecture patterns (chatbot, RAG pipeline, multi-step agent, …) used as starting points for estimates. | ## Try it Paste into Claude Code or Cursor after connecting: > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day ## Setup ```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ``` ## Links - Docs & tool reference: https://beforeyouship.dev/docs#mcp - Live calculator: https://beforeyouship.dev - Announcement: https://beforeyouship.dev/blog/query-llm-costs-from-claude-code
//beforeyouship — LLM cost modeling from your editor is a Model Context Protocol (MCP) server. It ranks #118,576 of 137,492 servers tracked on MCP Toplist. //beforeyouship — LLM cost modeling from your editor is listed on Smithery, and ships as a single rolling release with no explicit version metadata. It was first listed on Jun 11, 2026.
Ranks ahead of 18,916 of 137,492 servers on MCP Toplist.
Use //beforeyouship — LLM cost modeling from your editor
Hosted remote endpoint gated by authentication — connect via its URL and authenticate with the provider (OAuth flow or an API key/header, per its docs).
claude mcp add --transport http cost-model https://server.smithery.ai/beforeyouship/cost-model/mcpThis endpoint requires authentication — see the server’s docs for credentials.
[mcp_servers.cost-model]
url = "https://server.smithery.ai/beforeyouship/cost-model/mcp"Add to ~/.codex/config.toml. This endpoint requires authentication — see the server’s docs for credentials.
https://server.smithery.ai/beforeyouship/cost-model/mcpSettings → Connectors → “Add custom connector”, then paste this URL. This endpoint requires authentication — see the server’s docs for credentials.
{
"mcpServers": {
"cost-model": {
"url": "https://server.smithery.ai/beforeyouship/cost-model/mcp"
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (per project). This endpoint requires authentication — see the server’s docs for credentials.
{
"servers": {
"cost-model": {
"type": "http",
"url": "https://server.smithery.ai/beforeyouship/cost-model/mcp"
}
}
}Save as .vscode/mcp.json in your workspace. This endpoint requires authentication — see the server’s docs for credentials.
{
"mcpServers": {
"cost-model": {
"serverUrl": "https://server.smithery.ai/beforeyouship/cost-model/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json. This endpoint requires authentication — see the server’s docs for credentials.
{
"mcpServers": {
"cost-model": {
"url": "https://server.smithery.ai/beforeyouship/cost-model/mcp"
}
}
}This endpoint requires authentication — see the server’s docs for credentials.
Show your rank
Maintain this server? Add the live rank badge to your README — it updates automatically as the leaderboard changes.
[](https://mcptoplist.com/server/smithery%2Fbeforeyouship%2Fcost-model)<a href="https://mcptoplist.com/server/smithery%2Fbeforeyouship%2Fcost-model"><img src="https://mcptoplist.com/badge/smithery%2Fbeforeyouship%2Fcost-model.svg" alt="MCP Toplist: #118,576 of 137,492" /></a>Variants: append ?metric=score or ?metric=stars to the image URL.
Listed on 1 registry
Not versioned
This server is published through a registry that does not expose explicit version metadata, and no GitHub release tags were found on the linked repository. The listing tracks a single rolling release.
Frequently asked questions
- Is //beforeyouship — LLM cost modeling from your editor listed on the Official MCP Registry?
- //beforeyouship — LLM cost modeling from your editor is not on the Official MCP Registry. It is listed on Smithery.
- How many versions does //beforeyouship — LLM cost modeling from your editor have?
- //beforeyouship — LLM cost modeling from your editor ships as a single rolling release with no explicit version metadata.
Do you run this server?
Community projects list the MCP servers behind real agents and apps. Publish yours and this page will link to it.