anomalyco/models.dev

An open-source database of AI models.

What it solves

It addresses the lack of a single, comprehensive database for AI model specifications, pricing, and capabilities, providing a community-contributed source of truth for developers.

How it works

Data is stored as TOML files organized by provider and model. The project separates provider-agnostic model metadata (e.g., release date, capabilities) from provider-specific serving details (e.g., pricing, context limits). This data is then used to power a website and a public API that allows users to look up model IDs, metadata, and provider logos via JSON endpoints.

Who it’s for

Developers who need reliable, standardized metadata and pricing information for various AI models to integrate them into their applications or compare different providers.

Highlights

  • Provider-agnostic metadata: Separates the core facts about a model from how a specific provider serves it.
  • API access: Provides dedicated JSON endpoints for the full catalog, model-only metadata, and provider logos.
  • AI SDK integration: Uses Model IDs compatible with the AI SDK.
  • Community-driven: Open-source and community-contributed data updates.

Related

  • Dispatch
    Models.dev: Building an Open-Source Standard for AI Model Specifications

    An exploration of Models.dev, a community-driven database of AI model pricing, capabilities, and specs designed to provide a unified reference for developers.

  • Project
    OpenModelDB/open-model-database

    A community-driven database for discovering, comparing, and downloading over 600 AI image and video upscaling models with detailed metadata.

  • Project
    Ahmet-Dedeler/ai-llm-comparison

    An open-source AI model comparison tool that provides real-time pricing and feature comparisons across multiple LLM providers.

  • Project
    pydantic/genai-prices

    GenAI Prices is a multi‑language library (Python, JS/TS, Go) that supplies up‑to‑date pricing data and lookup logic for hundreds of LLM models across dozens of providers, supporting historic rates, tiered pricing, and daily price variations.

  • Project
    FB208/OpenBidKit_Yibiao

    OpenBidKit Yibiao is an open‑source Electron‑based desktop app that uses LLMs (OpenAI‑compatible, Ollama, LM Studio, etc.) to parse tender documents, generate full bid proposals (text, images, charts), manage a local knowledge base, and run quality checks such as plagiarism, typo, and logical error detection. It runs entirely on the user’s machine (Windows), stores data in SQLite, and is built with React, TypeScript, Vite, and a .NET 10 helper for Word/Open XML handling. Licensed under AGPL‑3.0.