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

@opencode-ai/models

v0.0.11

Published

Official typed client for the models.dev API — an open database of AI model capabilities, pricing, and limits

Readme

@opencode-ai/models

Official typed client for the Models.dev API.

npm install @opencode-ai/models

Usage

import { Models } from "@opencode-ai/models"

const client = Models.make()

const providers = await client.providers() // GET /api.json
providers["anthropic"]?.models["claude-opus-4-6"]?.cost?.input // USD per 1M tokens

const models = await client.models() // GET /models.json
models["anthropic/claude-opus-4-6"]?.knowledge // provider-agnostic metadata

const catalog = await client.catalog() // GET /catalog.json — both in one request

Options:

const client = Models.make({
  baseUrl: "https://models.dev", // default
  fetch: myFetch,                // proxies, polyfills, test doubles
  headers: { "x-extra": "1" },   // sent with every request
})

await client.providers({ signal: AbortSignal.timeout(5000) })

Errors are a single ModelsDevError with reason: "Transport" | "UnexpectedStatus" | "MalformedResponse" and the underlying cause.

Snapshot

A full copy of the database ships inside the package as a separate, tree-shakable entrypoint:

import snapshot, { providers, models, generatedAt } from "@opencode-ai/models/snapshot"

providers["anthropic"]?.models["claude-opus-4-6"]?.limit.context

Use it for no-network runtimes, tests, cold-start-sensitive paths, or as an explicit fallback:

const providers = await client.providers().catch(async () => (await import("@opencode-ai/models/snapshot")).providers)

The published snapshot is at most ~24h behind the live API (data releases are automated).

Effect

An Effect-native client lives at @opencode-ai/models/effect (requires the optional peer dependency effect):

import { Models } from "@opencode-ai/models/effect"
import { FetchHttpClient } from "effect/unstable/http"
import { Effect } from "effect"

const program = Effect.gen(function* () {
  const client = yield* Models.make()
  return yield* client.providers() // Effect<ProviderMap, ModelsDevError>
})

await program.pipe(Effect.provide(FetchHttpClient.layer), Effect.runPromise)

Transport comes from the environment's HttpClient service, so proxies, retries, tracing, and test transports compose the usual Effect way. For DI, Models.Service and Models.layer(options?) are provided:

const program = Effect.gen(function* () {
  const client = yield* Models.Service
  return yield* client.models()
})

program.pipe(Effect.provide(Models.layer().pipe(Layer.provide(FetchHttpClient.layer))))