Models & Registry

node-llm includes a comprehensive, built-in registry of hundreds of models using data from Parsera. This allows you to discover models and their capabilities programmatically.

Inspecting a Model

You can look up any supported model to check its context window, costs, and features.

import { LLM } from "@node-llm/core";

const model = LLM.models.find("gpt-4o");

if (model) {
  console.log(`Provider: ${model.provider}`);
  console.log(`Context Window: ${model.context_window} tokens`);
  console.log(`Input Price: $${model.pricing.text_tokens.standard.input_per_million}/1M`);
  console.log(`Output Price: $${model.pricing.text_tokens.standard.output_per_million}/1M`);
}

Discovery by Capability

You can filter the registry to find models that match your requirements.

Finding Vision Models

const visionModels = LLM.models.list().filter(m => 
  m.capabilities.includes("vision")
);

console.log(`Found ${visionModels.length} vision-capable models.`);
visionModels.forEach(m => console.log(m.id));

Finding Tool-Use Models

const toolModels = LLM.models.list().filter(m => 
  m.capabilities.includes("tools")
);

Finding Audio Models

const audioModels = LLM.models.list().filter(m => 
  m.capabilities.includes("audio_input")
);

Supported Providers

The registry includes models from:

• OpenAI (GPT-4o, GPT-3.5, DALL-E)
• Anthropic (Claude 3.5 Sonnet, Haiku, Opus)
• Google Gemini (Gemini 1.5 Pro, Flash)
• Vertex AI (via Gemini)

Custom Models & Endpoints

Sometimes you need to use models not in the registry, such as Azure OpenAI deployments, Local Models (Ollama/LM Studio), or brand new releases.

Using assumeModelExists

This flag tells node-llm to bypass the registry check.

Important: You MUST specify the provider when using this flag, as the system cannot infer it from the ID.

const chat = LLM.chat("my-custom-deployment", {
  provider: "openai", // Mandatory
  assumeModelExists: true
});

// Note: Capability checks are bypassed (assumed true) for custom models.
await chat.ask("Hello");

Custom Endpoints (e.g. Azure/Local)

To point to a custom URL (like an Azure endpoint or local proxy), configure the base URL globally.

LLM.configure({
  openaiApiBase: "https://my-azure-resource.openai.azure.com",
  openaiApiKey: process.env.AZURE_API_KEY
});

// Now valid for all OpenAI requests
const chat = LLM.chat("gpt-4", { provider: "openai" });