mcp server
mcp
Live LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required.
Description as published by the maintainer. Source
- version 1.0.0
- active
active — Registry entry last updated 2026-07-04.
What this server can do
5 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
cheapest_models(limit, sort_by, category, open_source)- Find the cheapest current models, ranked by input price, output price, or a blended cost. The generic ranking covers generative text models (embeddings, OCR and realtime models are excluded — they price different work); pass category to rank a specific pool instead, e.g. 'embedding'. Use to answer 'what is the cheapest model for <use case>'.
compare_models(model_ids)- Compare 2–5 models side by side on price, context window, and capabilities, with a verdict on which is cheapest for input, output, and a typical blended workload. Required: model_ids.
get_model_pricing(model_id)- Get full pricing and capability details for one model by its id (from search_models). Returns input/output/cached price per 1M tokens, blended cost, context window, modality, release date, and the modelpricewatch.com page URL. Required: model_id.
list_providers- List all tracked AI model providers (OpenAI, Anthropic, Google, etc.) with a short description and their pricing page.
search_models(limit, query, category, open_source)- Search the live LLM pricing database by model name, provider, or id. Returns matching models with current input/output prices (USD per 1M tokens), context window, modality, and category. Use this to answer 'how much does <model> cost' or 'what models does <provider> offer'.
Last successful function declaration observed on . Source: https://modelpricewatch.com/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://modelpricewatch.com/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| Package downloads | 42 downloads | Package downloads from the npm registry in this window. Includes continuous integration runs, mirrors and automated installs, so it overstates the number of human users. | 2026-07-30 to 2026-08-05 | npm | |
| Latest published version | 1.0.0 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-04 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| First listed in the MCP Registry | 2026-07-04 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| mcp tools declared | 5 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | modelpricewatch.com | |
| mcp endpoint status | ok | The server listed 5 functions when asked. | as of probe | modelpricewatch.com |
Where to get it
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json