io.github.AndrewAvery7/promptspend

up checked 2026-11-11T09:39:20.455Z

Unclaimed · Unverified

Publisher-provided title

PromptSpend

Publisher-provided description

LLM pricing where every rate carries its source and the date it was last confirmed.

Summary by lookupd

Estimates LLM API costs for a workload, finds cheaper comparable models, and looks up per-million-token prices with source and date.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http promptspend https://promptspend.dev/mcp

Claude Code, npm package (stdio)

claude mcp add promptspend -- npx -y @promptspend/mcp

Codex, remote (streamable-http)

codex mcp add promptspend --url https://promptspend.dev/mcp

Codex, npm package (stdio)

codex mcp add promptspend -- npx -y @promptspend/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "promptspend": {
      "url": "https://promptspend.dev/mcp"
    }
  }
}

Cursor, npm package (stdio) → .cursor/mcp.json

{
  "mcpServers": {
    "promptspend": {
      "command": "npx",
      "args": [
        "-y",
        "@promptspend/mcp"
      ]
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

get_price List price for one LLM in USD per million tokens, with its source and last-confirmed date. Returns disputed=true when two sources disagree, and close matches wh
estimate_cost Monthly cost of a described workload, or of measured usage, on each model. Accounts for history compounding, cache writes, long-context tiers and reasoning toke
find_cheaper Cheaper models that score at or above the given one on capability, costed on the same workload. Returns candidates to test, not a recommendation.

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.AndrewAvery7/promptspend.svg)](https://lookupd.com/servers/io.github.AndrewAvery7/promptspend)