ModelPickr republishes the Models.dev catalog under the MIT license. OpenRouter is an internal price check only and is not republished. Data last refreshed Oct 14, 2026, 05:43 PM UTC.
Sources
Where the numbers come from
Last fetch Oct 14, 2026, 05:43 PM UTC. 519 text models, 64 labs.
Models.dev
Primary source, republished with credit. The project is anomalyco/models.dev, MIT license. The refresh reads api.json and models.json. Provider docs are linked from model pages. A benchmark row is kept only when the source is the model's lab or the benchmark owner. Third-party leaderboards are omitted. A plain-text extract for assistants is at /llms.txt and /llms-full.txt.
Lab marks are a local subset of Lobe Icons, MIT license, copyright LobeHub. The files live in public/logos with that license text. Labs without a mark use a letter.
OpenRouter
GET /api/v1/models is fetched as an internal cross-check. Its fields are not stored and not shown on pages. The committed summary records our model id and which of input, output, cache read, or cache write disagreed, without their numbers.
Last check compared 188 models. 124 were within 2% or $0.02 per 1M tokens.64 disagreed. 298 of our priced models were absent. Disagreements do not replace the Models.dev price.
OpenRouter's terms have not been reviewed. Until they are, nothing from that API is published.
Not used yet
- Provider pricing pages (OpenAI, Anthropic, Google, and others). Their terms are unchecked, so they are not scraped.
- The Hugging Face Hub API. Weight links that Models.dev already publishes are kept; download counts are not pulled.
- Artificial Analysis and LLM Stats. Both restrict republishing.