# ModelPickr

> Which model for a job, and what it costs per month. Specs and prices are republished from Models.dev (MIT). Data last refreshed 2026-10-14T17:43:43.286Z.

ModelPickr is a static directory at https://modelpickr.com. It keeps text models from established labs that several providers sell, scores each job separately, and estimates a monthly bill from published token prices. A benchmark row counts only when the source is the model's lab or the benchmark owner. Artificial Analysis, OpenRouter, and LLM Stats are not republished. There is no site search URL. The models table filters in the browser.

## Key pages

- [Home](https://modelpickr.com/): job picker, catalog size, and the latest price and release changes.
- [Models](https://modelpickr.com/models): every text model, with input and output price, context, provider count, release date, and capabilities.
- [Labs](https://modelpickr.com/labs): one page per lab.
- [Jobs](https://modelpickr.com/best): coding agents, long-document Q&A, and summarization.
- [Coding agents](https://modelpickr.com/best/coding-agents): Which model should I use for a coding agent, and what will it cost each month? Status: indexed.
- [Long-document Q&A](https://modelpickr.com/best/long-document-qa): Which model should I use to ask questions of documents over 200,000 tokens, and what will it cost each month? Status: indexed.
- [Cheapest summarization](https://modelpickr.com/best/cheapest-summarization): Which model is the cheapest way to summarize a steady stream of documents, and what will it cost each month? Status: draft, noindex.
- [Compare](https://modelpickr.com/compare): pairwise pages inside a model family.
- [Calculator](https://modelpickr.com/calculator): monthly bill from requests per day, tokens, and cache hit rate.
- [Changes](https://modelpickr.com/changes): snapshot diff of releases, price moves, and removals. RSS at https://modelpickr.com/changes.rss.
- [Methodology](https://modelpickr.com/methodology): quality bar, citation rule, and the per-job score.
- [Sources](https://modelpickr.com/sources): Models.dev attribution and what is not republished.
- [Newsletter](https://modelpickr.com/newsletter): weekly email on new models and price changes, via Buttondown.
- [Full extract](https://modelpickr.com/llms-full.txt): methodology, current picks, and indexable model URLs.

## Optional

- [Sitemap](https://modelpickr.com/sitemap.xml): same document as https://modelpickr.com/sitemap-index.xml.