### Install LLM.js via npm

Source: https://github.com/themaximalist/llm.js/blob/main/README.md

Shows the command to install the LLM.js library using npm, the Node Package Manager.

```bash
npm install @themaximalist/llm.js
```

--------------------------------

### Install LLM.js via NPM

Source: https://github.com/themaximalist/llm.js/blob/main/public/index.html

This snippet shows the command to install the LLM.js library using npm, which is the standard package manager for Node.js.

```bash
npm install @themaximalist/llm.js
```

--------------------------------

### LLM.js Extended Response Example

Source: https://github.com/themaximalist/llm.js/blob/main/public/index.html

Illustrates how to get extended information from an LLM.js request, including content, token usage, the service provider, and the full conversation history.

```javascript
const response = await LLM("what are the primary colors?", { extended: true });
console.log(response.content);   // "The primary colors are red, blue, and yellow"
console.log(response.usage);     // { input_tokens: 6, output_tokens: 12, total_cost: 0.0001 }
console.log(response.service);   // "ollama" 
console.log(response.messages);  // Full conversation history
```

--------------------------------

### Basic LLM Initialization and Call (JavaScript)

Source: https://github.com/themaximalist/llm.js/blob/main/README.md

Provides a basic example of importing and using the LLM.js library as an async function for a single request, returning a string response.

```javascript
import LLM from "@themaximalist/llm.js"
await LLM("hello"); // Response: hi
```

--------------------------------

### System Instruction Configuration

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/interfaces/GoogleOptions.html

Defines the configuration for system instructions, which include parts with text content. This is used to guide the model's behavior.

```typescript
system_instruction?: { parts: { text: string }[] }
```

--------------------------------

### Connection Verification

Source: https://github.com/themaximalist/llm.js/blob/main/README.md

Verify your setup and API keys with built-in connection verification. This performs a light check to ensure services and API keys are working correctly.

```APIDOC
## Connection Verification

### Description
Tests your setup and API keys with built-in connection verification. This is a light check that doesn't perform a full LLM chat response; for non-local services, it detects if models can be fetched, and for local services, if an instance is running.

### Method
N/A (Library Usage)

### Endpoint
N/A (Library Usage)

### Parameters
N/A

### Request Example
```javascript
const llm = new LLM({ service: "openai" });
const isConnected = await llm.verifyConnection();
console.log(isConnected); // true if API key and service work
```
```

--------------------------------

### LLM.js Chat with System Prompt and Streaming

Source: https://github.com/themaximalist/llm.js/blob/main/public/index.html

Shows how to configure a system message for the LLM and then stream chat responses using LLM.js, illustrating a conversational AI setup.

```javascript
const llm = new LLM({ stream: false });
llm.system("You are a friendly AI assistant");
const stream = await llm.chat("hello, how are you?", { stream: true });
for await (const chunk of stream) {
  process.stdout.write(chunk);
}
```

--------------------------------

### Streaming Response Example with LLM.js

Source: https://github.com/themaximalist/llm.js/blob/main/public/index.html

Illustrates how to handle streaming responses from an LLM using LLM.js. This allows for real-time display of the LLM's output as it's being generated.

```javascript
import { LLM } from "@llm.js/core"

const llm = new LLM({
  provider: "openai",
  model: "gpt-3.5-turbo",
  apiKey: "YOUR_API_KEY"
})

async function streamExample() {
  const stream = await llm.stream(
    "Tell me a short story."
  )

  for await (const chunk of stream) {
    process.stdout.write(chunk)
  }
  console.log()
}

streamExample()
```

--------------------------------

### Initialize Theme and Show Page (JavaScript)

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/functions/parsers.markdown.html

Sets the document theme based on local storage and displays the application page after a short delay. It handles cases where the 'app' object might not be immediately available.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Initialize Theme and Show App - JavaScript

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/modules.html

Sets the document theme from local storage and conditionally displays the application or removes a display style from the body after a short delay. This script likely handles initial UI setup and theme persistence.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Initialize Theme and Show App

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/index.html

This snippet initializes the document's theme based on local storage and conditionally shows the application page or removes the display style from the body. It waits for 500ms before executing.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Install LLM.js using npm

Source: https://github.com/themaximalist/llm.js/blob/main/public/index.html

This snippet shows the command to install the LLM.js library using npm, the Node Package Manager. It's the standard way to add LLM.js as a dependency to your JavaScript project.

```bash
npm install @llm.js/core
```

--------------------------------

### Initialize Theme and Show App

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/interfaces/Options.html

Sets the theme from local storage and controls the initial display of the application body. It delays the visibility of the app content until after a short timeout.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Get and Refresh All Models with LLM.js

Source: https://github.com/themaximalist/llm.js/blob/main/README.md

Demonstrates how to retrieve all cached language models and refresh the list from external sources using the ModelUsage class. It also shows how to get details for a specific model, such as its input cost per token and maximum input tokens.

```javascript
import { ModelUsage } from "@themaximalist/llm.js";

// Get all cached models
const allModels = ModelUsage.getAll();
console.log(allModels.length); // 100+

// Refresh from latest sources  
const refreshedModels = await ModelUsage.refresh();
console.log(refreshedModels.length); // Even more models

// Get specific model info
const gpt4 = ModelUsage.get("openai", "gpt-4o");
console.log(gpt4.input_cost_per_token);  // 0.0000025
console.log(gpt4.max_input_tokens);      // 128000
```

--------------------------------

### LLM Initialization with Options

Source: https://github.com/themaximalist/llm.js/blob/main/README.md

Shows how to instantiate and configure LLM.js with various options. These options control the LLM service provider, API key, model selection, response generation parameters, and more.

```javascript
const llm = new LLM(input, {
  service: "openai",        // LLM service provider
  apiKey: "sk-123"          // apiKey
  model: "gpt-4o",          // Specific model
  max_tokens: 1000,         // Maximum response length
  temperature: 0.7,         // "Creativity" (0-2)
  stream: true,             // Enable streaming
  extended: true,           // Extended responses with metadata
  messages: [],             // message history
  think: true,              // Enable thinking mode
  parser: LLM.parsers.json, // Content parser
  tools: [...],             // Available tools
  max_thinking_tokens: 500, // Max tokens for thinking
});
```

--------------------------------

### GET /models/customs

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/ModelUsage.html

Retrieves all custom model configurations across all services and models.

```APIDOC
## GET /models/customs

### Description
Retrieves all custom model configurations available in the system.

### Method
GET

### Endpoint
/models/customs

### Parameters
No parameters required.

### Response
#### Success Response (200)
- **customModels** (Record<string, ModelUsageType[]>) - An object where keys are service names and values are arrays of model usage types.

#### Response Example
```json
{
  "openai": [
    {
      "service": "openai",
      "model": "gpt-3.5-turbo",
      "usage": 10000
    }
  ],
  "anthropic": [
    {
      "service": "anthropic",
      "model": "claude-2",
      "usage": 5000
    }
  ]
}
```
```

--------------------------------

### Initialize Theme and Show App Page

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/xAI.html

This snippet initializes the document's theme from local storage and controls the display of the application page. It hides the body initially and then reveals the page content after a short delay, ensuring the app is ready.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Switching LLM Models and Providers

Source: https://github.com/themaximalist/llm.js/blob/main/README.md

Illustrates how to easily switch between different Large Language Models and providers using LLM.js. This includes examples for local providers like Ollama and remote services like OpenAI, Anthropic, Google, and xAI.

```javascript
// Defaults to Ollama (local)
await LLM("the color of the sky is");

// OpenAI
await LLM("the color of the sky is", { model: "gpt-4o-mini", service: "openai" });

// Anthropic
await LLM("the color of the sky is", { model: "claude-3-5-sonnet-latest", service: "anthropic" });

// Google
await LLM("the color of the sky is", { model: "gemini-1.5-pro", service: "google" });

// xAI
await LLM("the color of the sky is", { service: "xai", model: "grok-beta" });

// DeepSeek with thinking
await LLM("solve this puzzle", { service: "deepseek", model: "deepseek-reasoner", think: true });

// Ollama (local)
await LLM("the color of the sky is", { model: "llama3.2:3b", service: "ollama" });
```

--------------------------------

### URL Management API

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/Groq.html

Provides endpoints to get URLs related to chat and model information.

```APIDOC
## GET /chat/url

### Description
Retrieves the URL for chat-related operations.

### Method
GET

### Endpoint
/chat/url

### Parameters
#### Path Parameters
None

#### Query Parameters
- **opts** (Options) - Required - Options for the chat URL.

### Request Example
```json
{
  "opts": {}
}
```

### Response
#### Success Response (200)
- **urls** (string[]) - An array of chat-related URLs.

#### Response Example
```json
{
  "urls": ["https://api.example.com/chat"]
}
```
```

```APIDOC
## GET /models/url

### Description
Retrieves the base URL for accessing model information.

### Method
GET

### Endpoint
/models/url

### Parameters
None

### Response
#### Success Response (200)
- **urls** (string[]) - An array containing the model endpoint URL.

#### Response Example
```json
{
  "urls": ["https://api.example.com/models"]
}
```
```

--------------------------------

### Set Theme and Show Page - JavaScript

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/modules/parsers.html

Initializes the document's theme from local storage and conditionally displays the application page after a short delay. If the application object 'app' is not available, it reverts to showing the body element.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Get Models URL

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/Google.html

Retrieves the URL for fetching models. This function overrides the base LLM implementation.

```typescript
getModelsUrl(): string
```

--------------------------------

### Get Models URL from LLM.ts

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/APIv1.html

Retrieves the URL for accessing model information. This function is inherited from the base LLM class.

```typescript
getModelsUrl(): string
```

--------------------------------

### Initialize ModelUsage and Theme Setting

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/ModelUsage.html

Sets the document theme from local storage and prepares the application by initially hiding the body and then revealing the app's main page after a short delay.

```typescript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### GET /models/custom

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/ModelUsage.html

Retrieves custom model configurations for a specific service and model. Returns null if no custom configuration is found.

```APIDOC
## GET /models/custom

### Description
Retrieves custom model configurations based on service and model identifiers.

### Method
GET

### Endpoint
/models/custom

### Parameters
#### Query Parameters
- **service** (string) - Required - The service identifier for the model.
- **model** (string) - Required - The model identifier.

### Response
#### Success Response (200)
- **usageData** (ModelUsageType[]) - An array of model usage types or null.

#### Response Example
```json
[
  {
    "service": "openai",
    "model": "gpt-3.5-turbo",
    "usage": 10000
  }
]
```
```

--------------------------------

### Get Models URL

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/LLM.html

Retrieves the URL endpoint for fetching model information. This method returns the models URL as a string.

```typescript
getModelsUrl(): string
```

--------------------------------

### Basic Chat Example with LLM.js

Source: https://github.com/themaximalist/llm.js/blob/main/public/index.html

Demonstrates a simple chat interaction using LLM.js. It initializes the LLM, sends a user message, and receives a response. This requires setting up the LLM provider and model.

```javascript
import { LLM } from "@llm.js/core"

const llm = new LLM({
  provider: "openai",
  model: "gpt-3.5-turbo",
  apiKey: "YOUR_API_KEY"
})

async function chatExample() {
  const response = await llm.chat(
    "Hello, how are you?"
  )
  console.log(response)
}

chatExample()
```

--------------------------------

### Get LLM Options

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/LLM.html

Retrieves the default options for LLM interactions. This accessor returns an object conforming to the 'Options' interface.

```typescript
get llmOptions(): [Options](../interfaces/Options.html)
```

--------------------------------

### Theme Setting and Initialization

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/interfaces/Tool.html

This JavaScript snippet sets the document's theme based on local storage or defaults to 'os'. It then hides the body content and uses a timeout to reveal it, potentially showing an application page if available.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Theme and Display Initialization

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/interfaces/GoogleTool.html

Initializes the theme based on local storage and sets up a delay for displaying the page content. This code snippet handles the initial loading state and theme persistence.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Get Models by Service

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/ModelUsage.html

Retrieves a list of all models associated with a specific service, or all models if no service is provided. Returns an array of ModelUsageType.

```typescript
getByService(service?: string): ModelUsageType[][]
```

--------------------------------

### Get Models URL (TypeScript)

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/Groq.html

Retrieves the URL endpoint for fetching model information. Returns a string representing the models URL.

```typescript
getModelsUrl(): string
```

--------------------------------

### Set Theme from Local Storage and Show App

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/types/Input.html

This snippet sets the document's theme based on local storage or defaults to 'os'. It then hides the body and shows the app page after a 500ms delay, or removes the display property if the app is not available. This is commonly used for initial theme setup on page load.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Get Default Model Usage (TypeScript)

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/Groq.html

Retrieves the default usage type for a given model. Returns a ModelUsageType enum value.

```typescript
getDefaultModelUsage(model: Model): ModelUsageType
```

--------------------------------

### Initialize Theme and Application Display

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/variables/default.html

This script sets the document's theme based on local storage or defaults to 'os'. It then hides the body and reveals the application or the body after a 500ms delay to ensure proper loading.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Get Models URL (TypeScript)

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/xAI.html

Retrieves the URL for fetching the list of available models. This function returns the URL as a string.

```TypeScript
getModelsUrl(): string
```

--------------------------------

### LLMInterface - Constructor Overloads

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/interfaces/LLMInterface.html

Provides different ways to instantiate the LLMInterface, with or without input and options.

```APIDOC
## Constructors

### new LLMInterface(input: Input, options?: Options): LLMServices

**Description**: Initializes a new LLMInterface with input and optional configurations.

**Parameters**:
*   `input` (Input): The input for the LLM service.
*   `options` (Options, optional): Additional options for configuring the LLM service.

**Returns** (LLMServices): An instance of LLMServices.

### new LLMInterface(options: Options): LLMServices

**Description**: Initializes a new LLMInterface with optional configurations.

**Parameters**:
*   `options` (Options): Options for configuring the LLM service.

**Returns** (LLMServices): An instance of LLMServices.

### new LLMInterface(): LLMServices

**Description**: Initializes a new LLMInterface with default configurations.

**Returns** (LLMServices): An instance of LLMServices.
```

--------------------------------

### Get Quality Models

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/Google.html

Fetches a list of models specifically filtered by quality. This function is inherited from the base LLM class.

```typescript
getQualityModels(): Promise<Model[]>
```

--------------------------------

### Apply Theme and Show Page

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/functions/parsers.json.html

This JavaScript snippet applies a theme from local storage to the document's root element and then shows the application page after a short delay. It handles cases where the 'app' object might not be immediately available.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Get LLM Parsers

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/LLM.html

Retrieves the parsers used for processing LLM responses. This accessor returns an object conforming to the 'Parsers' interface.

```typescript
get parsers(): [Parsers](../interfaces/Parsers.html)
```

--------------------------------

### Set Theme and Show Page (JavaScript)

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/functions/parsers.codeBlock.html

Sets the theme based on local storage and controls the page's display after a delay, potentially showing the app page or removing display properties. This script is likely for initializing the UI.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Get LLM Headers

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/LLM.html

Retrieves the headers required for LLM requests. This accessor returns a Record of string keys and string values.

```typescript
get llmHeaders(): Record<string, string>
```

--------------------------------

### Set Theme and Initialize App

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/types/ModelUsageType.html

This JavaScript code snippet is responsible for initializing the application's theme based on local storage and then conditionally displaying the application's main page. It includes a delay to ensure the app is ready before showing the content.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Get LLM Chat URL

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/LLM.html

Retrieves the URL endpoint for chat-related operations. This accessor returns a string representing the chat URL.

```typescript
get chatUrl(): string
```

--------------------------------

### Get Default Model Usage from LLM.ts

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/APIv1.html

Retrieves the default usage type for a given model. This method is inherited from the base LLM class.

```typescript
getDefaultModelUsage(model: Model): ModelUsageType
```

--------------------------------

### Initialize Theme and Display Settings

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/types/MessageContent.html

This script sets the document theme based on local storage and controls the initial display of the body element, revealing the app content after a short delay.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### LLMInterface Constructor Overloads

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/interfaces/LLMInterface.html

Demonstrates the multiple ways to construct an LLMInterface instance. It supports initialization with input and options, only options, or no arguments, returning LLMServices. These constructors are key for setting up LLM interactions with varying configurations.

```typescript
new LLMInterface(input: [Input](../types/Input.html), options?: [Options](Options.html)): [LLMServices](../types/LLMServices.html);
```

```typescript
new LLMInterface(options: [Options](Options.html)): [LLMServices](../types/LLMServices.html);
```

```typescript
new LLMInterface(): [LLMServices](../types/LLMServices.html);
```

--------------------------------

### Get Chat URL from LLM.ts

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/APIv1.html

Generates a chat URL based on provided options. This function inherits its implementation from the base LLM class.

```typescript
getChatUrl(opts: Options): string
```

--------------------------------

### Set Document Theme and Show App (JavaScript)

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/types/ParserResponse.html

Sets the document's theme based on local storage and controls the initial display of the application. It waits for 500ms before showing the page or removing the display style.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Get Chat URL API

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/Anthropic.html

Generates a URL for initiating a chat session. This method inherits its functionality from the base LLM class.

```APIDOC
## GET /api/chat/url

### Description
Generates a URL to start a new chat session.

### Method
GET

### Endpoint
/api/chat/url

### Parameters
#### Query Parameters
- **opts** (Options) - Required - Configuration options for the chat session.

### Response
#### Success Response (200)
- **url** (string) - The generated URL for the chat session.

#### Response Example
```json
{
  "url": "https://chat.example.com/session/12345"
}
```
```

--------------------------------

### LLM.js: Initialize Theme and Show Page

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/Attachment.html

This snippet sets the document's theme based on local storage and controls the initial display of the page content. It hides the body and then reveals it after a short delay, either by showing a specific page via `window.app.showPage()` or by removing the display property.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Get Quality Models (TypeScript)

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/Groq.html

Fetches a list of models specifically filtered for quality. Returns a promise that resolves to an array of Model objects.

```typescript
getQualityModels(): Promise<Model[]>
```

--------------------------------

### xAI Class Constructor

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/xAI.html

Initializes a new instance of the xAI class. It can optionally accept initial options or input for configuring the language model interaction.

```APIDOC
## new xAI

### Description
Initializes a new instance of the xAI class. It can optionally accept initial options or input for configuring the language model interaction.

### Method
Constructor

### Parameters
#### Path Parameters
- None

#### Query Parameters
- None

#### Request Body
- **input** (Options | Input) - Optional. Initial configuration or input for the language model.
- **options** (Options) - Optional. Additional options for configuring the xAI instance. Defaults to an empty object.

### Request Example
```json
{
  "input": {
    "model": "gpt-4",
    "max_tokens": 1000
  },
  "options": {
    "apiKey": "YOUR_API_KEY"
  }
}
```

### Response
#### Success Response (200)
- N/A (Constructor does not return a value in the traditional sense, it creates an instance)

#### Response Example
```json
// Instance of xAI created
```
```

--------------------------------

### Get Models URL API

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/xAI.html

Retrieves the URL for accessing model information. This method returns a string representing the models URL.

```APIDOC
## getModelsUrl

### Description
Retrieves the URL for accessing model information. This method returns a string representing the models URL.

### Method
GET

### Endpoint
/getModelsUrl

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Request Example
```json
{} 
```

### Response
#### Success Response (200)
- **modelsUrl** (string) - The URL to access model information.
```

--------------------------------

### Set Theme and Initial Display

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/types/ServiceName.html

Sets the document theme based on local storage and manages the initial display of the application body. It waits for the app to be ready or a timeout to occur before showing the page content.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Get Models API

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/xAI.html

Fetches a list of models, optionally filtering by quality. Returns a promise that resolves to an array of Model objects.

```APIDOC
## getModels

### Description
Fetches a list of models, optionally filtering by quality. Returns a promise that resolves to an array of Model objects.

### Method
GET

### Endpoint
/getModels

### Parameters
#### Path Parameters
None

#### Query Parameters
- **quality_filter** (QualityFilter) - Optional - A filter to apply to the model list based on quality.

#### Request Body
None

### Request Example
```json
{
  "quality_filter": {
    "minQuality": 0.8
  }
}
```

### Response
#### Success Response (200)
- **models** (Model[]) - An array of Model objects matching the quality filter.
```

--------------------------------

### Get Models with Quality Filter

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/Google.html

Fetches a list of models, optionally filtering them by quality. This function is inherited from the base LLM class.

```typescript
getModels(quality_filter?: QualityFilter): Promise<Model[]>
```

--------------------------------

### LLM System Prompts for Specialization

Source: https://github.com/themaximalist/llm.js/blob/main/README.md

Explains how to use system prompts with LLM.js to specialize the model for specific tasks. This example sets a system prompt to make the LLM a friendly chat bot and then engages in a conversation.

```javascript
const llm = new LLM();
llm.system("You are a friendly chat bot.");
await llm.chat("what's the color of the sky in hex value?"); // Response: sky blue
await llm.chat("what about at night time?"); // Response: darker value (uses previous context)
```

--------------------------------

### Get Default Model Usage

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/Google.html

Retrieves the default usage type for a given model. This function is inherited from the base LLM class.

```typescript
getDefaultModelUsage(model: Model): ModelUsageType
```

--------------------------------

### Setting API Keys in Environment (Node.js)

Source: https://github.com/themaximalist/llm.js/blob/main/README.md

Illustrates how to set API keys for various LLM services as environment variables in a Node.js environment for automatic detection by LLM.js.

```bash
export OPENAI_API_KEY=...
export ANTHROPIC_API_KEY=...
export GOOGLE_API_KEY=...
export GROQ_API_KEY=...
export DEEPSEEK_API_KEY=...
export XAI_API_KEY=...
```

--------------------------------

### Get Chat URL

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/Google.html

Generates a URL for chat interactions based on provided options. This function overrides the base LLM implementation.

```typescript
getChatUrl(opts: Options): string
```

--------------------------------

### Set Theme and Show Page

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/types/LLMServices.html

This JavaScript code snippet initializes the theme based on local storage and then dynamically displays the page content after a short delay, either by calling app.showPage() or removing the display:none property.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Get Quality Models

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/LLM.html

Fetches a list of models that have passed a quality assessment. This method returns a Promise resolving to an array of 'Model' objects.

```typescript
getQualityModels(): Promise<[Model](../types/Model.html)[]>
```

--------------------------------

### Get LLM Models URL

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/LLM.html

Retrieves the URL endpoint for fetching available models. This accessor returns a string representing the models URL.

```typescript
get modelsUrl(): string
```

--------------------------------

### Switch LLM Models Using LLM.js

Source: https://github.com/themaximalist/llm.js/blob/main/public/index.html

Demonstrates how to switch between various Large Language Models (LLMs) using the LLM.js library. It shows examples for default local models (Ollama), OpenAI, Anthropic, Google, xAI, DeepSeek, and specific Ollama models. The function call includes the prompt and an optional configuration object specifying the model and service provider.

```javascript
await LLM("the color of the sky is");

await LLM("the color of the sky is", { model: "gpt-4o-mini", service: "openai" });

await LLM("the color of the sky is", { model: "claude-3-5-sonnet-latest", service: "anthropic" });

await LLM("the color of the sky is", { model: "gemini-1.5-pro", service: "google" });

await LLM("the color of the sky is", { service: "xai", model: "grok-beta" });

await LLM("solve this puzzle", { service: "deepseek", model: "deepseek-reasoner", think: true });

await LLM("the color of the sky is", { model: "llama3.2:3b", service: "ollama" });
```

--------------------------------

### Get Model by Service and Name

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/ModelUsage.html

Retrieves a specific model based on its service and name, with an optional quality filter. Returns the model details or null.

```typescript
get(
    service: string,
    model: string,
    quality_filter?: QualityFilter,
): null | ModelUsageType[]
```

--------------------------------

### Setting System Prompts with LLM.js

Source: https://github.com/themaximalist/llm.js/blob/main/public/index.html

Explains how to use the `llm.system()` method in LLM.js to instruct the model to specialize in specific tasks, enhancing its behavior in subsequent interactions.

```javascript
const llm = new LLM();
llm.system("You are a friendly chat bot.");
await llm.chat("what's the color of the sky in hex value?");
await llm.chat("what about at night time?");
```

--------------------------------

### Get Specific Model Information

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/ModelUsage.html

Retrieves information for a specific model, optionally filtering by quality. It returns the model usage details or null if not found.

```typescript
getModel(model: string, quality_filter?: QualityFilter): null | ModelUsageType[]
```

--------------------------------

### Get Models URL

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/DeepSeek.html

Retrieves the URL endpoint for fetching model information. This function does not take any parameters and returns a string. Inherited from APIv1.

```typescript
getModelsUrl(): string
```

--------------------------------

### Fetch Latest LLM Models with LLM.js

Source: https://github.com/themaximalist/llm.js/blob/main/public/index.html

Demonstrates how to instantiate the LLM class and fetch a list of all available models from supported providers. It shows how to log the count of models and inspect the details of the first model in the list.

```javascript
const llm = new LLM({ service: "openai" });
const models = await llm.fetchModels();

console.log(models.length); // 50+ models
console.log(models[0]);     // { name: "gpt-4o", created: Date, service: "openai", ... }
```

--------------------------------

### Set Theme and Show Page - JavaScript

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/types/Model.html

This snippet sets the theme based on local storage and displays the page content after a short delay, potentially showing the app's main page or removing a display:none style.

```javascript
document.documentElement.dataset.theme = localStorage.getItem("tsd-theme") || "os";
document.body.style.display="none";
setTimeout(() => window.app?app.showPage():document.body.style.removeProperty("display"),500)
```

--------------------------------

### Get Model Response

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/Anthropic.html

Processes generic data to extract a string response from the model. This method is inherited from the LLM class and defined in LLM.ts.

```typescript
response(data: any): string[]
```

--------------------------------

### Get Models URL API

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/Anthropic.html

Retrieves the URL endpoint for accessing model information. This method inherits its functionality from the base LLM class.

```APIDOC
## GET /api/models/url

### Description
Retrieves the URL where model information can be accessed.

### Method
GET

### Endpoint
/api/models/url

### Response
#### Success Response (200)
- **url** (string) - The URL for model information.

#### Response Example
```json
{
  "url": "https://api.example.com/v1/models"
}
```
```

--------------------------------

### Configure Custom Services with LLM.js

Source: https://github.com/themaximalist/llm.js/blob/main/README.md

Demonstrates how to configure and use custom LLM services by providing a custom service object with specific API details like `baseUrl`, `model`, and `apiKey`. It also shows how to extend the `LLM.APIv1` class for more complex custom service implementations.

```javascript
const llm = new LLM({
    service: "together",
    baseUrl: "https://api.together.xyz/v1",
    model: "meta-llama/Llama-3-70b-chat-hf",
    apiKey,
});
```

```javascript
class Together extends LLM.APIv1 {
    static readonly service: ServiceName = "together";
    static DEFAULT_BASE_URL: string = "https://api.together.xyz/v1";
    static DEFAULT_MODEL: string = "meta-llama/Llama-3-70b-chat-hf";
}

const llm = new Together();
```

```javascript

LLM.register(Together);
const llm = new LLM({ service: "together" });
```

--------------------------------

### Get Models URL in LLM.ts

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/Anthropic.html

Retrieves the base URL for accessing model information. This function returns a string and is inherited from the LLM class.

```typescript
getModelsUrl(): string;
```

--------------------------------

### LLM.js Configuration Options

Source: https://github.com/themaximalist/llm.js/blob/main/public/index.html

Provides an overview of the comprehensive configuration options available for the LLM.js constructor, including service providers, API keys, model selection, streaming, and more.

```javascript
const llm = new LLM(input, {
  service: "openai",
  apiKey: "sk-123",
  model: "gpt-4o",
  max_tokens: 1000,
  temperature: 0.7,
  stream: true,
  extended: true,
  messages: [],
  think: true,
  parser: LLM.parsers.json,
  tools: [...],
  max_thinking_tokens: 500,
});

// Key Options:
// service: Provider (`openai`, `anthropic`, `google`, `xai`, `groq`, `deepseek`, `ollama`)
// apiKey: API key for service, if not specified attempts to read from environment
// model: Specific model name (auto-detected from service if not provided)
// stream: Enable real-time streaming responses
// extended: Return detailed response with usage, costs, and metadata
// think: Enable reasoning mode for supported models
// temperature: Controls randomness (0 = deterministic, 2 = very creative)
```

--------------------------------

### Get the URL for models in LLM.js

Source: https://github.com/themaximalist/llm.js/blob/main/public/docs/classes/OpenAI.html

Retrieves the URL endpoint for fetching models. This function inherits from the base LLM class and returns a string.

```typescript
getModelsUrl(): string
```