npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

modelpedia

v0.0.5

Published

Open catalog of AI model data — specs, pricing, and capabilities across 30+ providers and 4000+ models

Readme

modelpedia

Open catalog of AI model data — specs, pricing, and capabilities across 30+ providers and 4000+ models.

npm version license

Install

npm install modelpedia

Usage

import {
  allModels,
  providers,
  getModel,
  getProvider,
  getActiveModels,
  getModelsByProvider,
  getModelsByFamily,
  getModelsByCreator,
} from "modelpedia";

// All models (4000+)
console.log(allModels.length);

// Find a specific model
const model = getModel("openai", "gpt-4o");
console.log(model?.pricing); // { input: 2.5, output: 10, ... }

// Get all active (non-deprecated) models
const active = getActiveModels();

// List models by provider
const openaiModels = getModelsByProvider("openai");

// List models by family
const gpt4oFamily = getModelsByFamily("gpt-4o");

// List models by creator (useful for aggregators like OpenRouter)
const anthropicModels = getModelsByCreator("anthropic");

// Get provider info
const provider = getProvider("anthropic");
console.log(provider?.name); // "Anthropic"
console.log(provider?.api_url); // "https://api.anthropic.com/v1"

Per-provider imports

Import only the provider you need for smaller bundle size:

import { provider, models } from "modelpedia/openai";
console.log(provider.name); // "OpenAI"
console.log(models.length); // 151

import { models as anthropicModels } from "modelpedia/anthropic";
import { models as googleModels } from "modelpedia/google";

Available: modelpedia/openai, modelpedia/anthropic, modelpedia/google, modelpedia/mistral, modelpedia/deepseek, modelpedia/xai, and 24 more.

Data Structure

Model

| Field | Type | Description | |-------|------|-------------| | id | string | Model identifier used in API calls | | name | string | Human-readable display name | | provider | string | Provider ID (e.g. "openai") | | created_by | string | Original creator (may differ from provider) | | family | string? | Model family/series (e.g. "gpt-4o") | | description | string? | Model description | | tagline | string? | One-line summary | | status | "active" \| "deprecated" \| "preview" | Lifecycle status | | model_type | string? | chat, reasoning, embed, image, video, tts, transcription, moderation, rerank, code | | context_window | number? | Default context window (tokens) | | max_output_tokens | number? | Maximum output tokens | | knowledge_cutoff | string? | Model's effective knowledge boundary (YYYY-MM or YYYY-MM-DD) | | training_data_cutoff | string? | Training data cutoff date (may differ from knowledge_cutoff) | | pricing | ModelPricing? | Pricing per 1M tokens + detailed tiers | | capabilities | ModelCapabilities? | vision, tool_call, streaming, reasoning, etc. | | modalities | ModelModalities? | Input/output modality support (text, image, audio, video) | | tools | string[]? | Supported tools (function_calling, web_search, mcp, etc.) | | endpoints | string[]? | Supported API endpoints (chat_completions, responses, batch, etc.) | | successor | string? | Recommended replacement model (for deprecated models) | | performance | number? | Intelligence rating (1-5) | | reasoning | number? | Reasoning rating (1-5) | | speed | number? | Speed rating (1-5) | | architecture | string? | Model architecture (transformer, moe, ssm, hybrid) | | open_weight | boolean? | Whether model weights are publicly available | | license | string? | SPDX ID, custom name, or "proprietary" | | parameters | number? | Total parameters in billions | | active_parameters | number? | Active parameters for MoE models |

Pricing

Flat fields for quick access:

model.pricing?.input       // USD per 1M input tokens
model.pricing?.output      // USD per 1M output tokens
model.pricing?.cached_input // USD per 1M cached input tokens
model.pricing?.batch_input  // USD per 1M batch input tokens

Detailed tiers for models with multiple pricing categories:

model.pricing?.tiers  // PricingTier[] — text tokens, audio tokens, image generation, etc.

Provider

| Field | Type | Description | |-------|------|-------------| | id | string | Provider identifier | | name | string | Display name | | region | string | Country code (ISO 3166-1 alpha-2) | | url | string | Website URL | | api_url | string | API base URL | | docs_url | string | Documentation URL | | pricing_url | string | Pricing page URL |

Providers

Alibaba Cloud, Amazon Bedrock, Anthropic, Azure, Baseten, Cerebras, Cloudflare (Workers AI, AI Gateway), Cohere, Cursor, DeepSeek, Fireworks, Google, Groq, Hugging Face, Meta, Minimax, Mistral, Moonshot, NVIDIA, Ollama, OpenAI, OpenCode, OpenRouter, Perplexity, Qwen, Together AI, Vercel, Vertex AI, xAI, and Z.AI.

Data Updates

Model data is automatically fetched from provider APIs daily. Community contributions are welcome — see CONTRIBUTING.md.

License

MIT