Metadata-Version: 2.5
Name: llmledger-mcp
Version: 0.1.0
Summary: Which AI model, and what it costs: LiteLLM prices, Arena ratings and price history, inside Claude and other AI apps.
Project-URL: Homepage, https://pouriaetab.github.io/llmledger/
Project-URL: Source, https://github.com/pouriaetab/llmledger/tree/main/mcp
Project-URL: Issues, https://github.com/pouriaetab/llmledger/issues
License-Expression: MIT
License-File: LICENSE
Keywords: fastmcp,litellm,llm,mcp,model selection,pricing
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Requires-Dist: fastmcp==4.1.0
Description-Content-Type: text/markdown

# llmledger-mcp

<!-- mcp-name: io.github.pouriaetab/llmledger -->

Ask Claude (or Cursor, ChatGPT desktop, any app that speaks MCP) which AI model to use and what it
costs, in the middle of your work. The answers come from [llmledger](https://pouriaetab.github.io/llmledger/):
LiteLLM's public price catalogue, Arena's ratings by task, and every price change since 2023 with how
likely a price is to change next. Rebuilt every day.

## Install

Needs [uv](https://docs.astral.sh/uv/). Nothing to host and no keys: the plug-in runs on your computer
and reads the day's data from the llmledger page, cached for a day, with a bundled copy for offline use.

Claude Code:

```bash
claude mcp add llmledger -- uvx llmledger-mcp
```

Claude Desktop (Settings, Developer, Edit config) or Cursor (`.cursor/mcp.json`):

```json
{
  "mcpServers": {
    "llmledger": { "command": "uvx", "args": ["llmledger-mcp"] }
  }
}
```

A LiteLLM proxy can offer it to a whole team through its MCP gateway, as a stdio server with the same
command.

## What you can ask

| Tool | For example |
|---|---|
| `suggest_for_project` | "Which model and effort for this project?" with the starting prompt; `pay` can be `claude` or `chatgpt` to compare within a plan |
| `compare_models` | "Opus 5.5 or Fable 5.1 for coding, and when is Fable cheaper?" |
| `estimate_cost` | "What do 2,000 calls a day of 10K tokens in and 1K out cost on these three?" |
| `find_models` | "The best rated coding models under $10 per 1M answer tokens that read images" |
| `price_history` | "Has Claude Opus 5.5's price changed, and how likely is it to change soon?" |

Plus a resource, `llmledger://snapshot` (data dates and sources), and a prompt, `pick_a_model`.

## Good to know

- Costs and ratings are estimates. Arena ratings say which answers people preferred, not what will work
  best for you. Plan use (Claude, ChatGPT) assumes a plan runs down in step with API prices, because
  plans do not publish per-model limits. Not financial or procurement advice.
- Effort levels come from LiteLLM; the suggested level is a rule of thumb. No open source measures
  tokens per task at each effort level yet.
- Set `LLMLEDGER_DATA` to a local data.json or another address to use your own copy.

## Data and licences

Prices: LiteLLM's `model_prices_and_context_window.json` (MIT). Ratings: the Arena leaderboard
(CC BY 4.0). Price history and outlook: [llmledger](https://github.com/pouriaetab/llmledger) (MIT).
Built with [FastMCP](https://github.com/PrefectHQ/fastmcp) (Apache-2.0). Independent; not affiliated
with BerriAI, LiteLLM or Arena.
