### C# SDK Example

Source: https://docs.llmgateway.io/quick-start

Example demonstrating LLM Gateway integration using the C# SDK. Ensure the NuGet package is installed.

```csharp
using LLMGateway;

var apiKey = Environment.GetEnvironmentVariable("LLM_GATEWAY_API_KEY");
var llm = new LLMGatewayClient(apiKey);

var response = await llm.Completions.CreateAsync(
    model: "gpt-3.5-turbo",
    prompt: "Hello world"
);

Console.WriteLine(response.Choices[0].Message.Content);
```

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

### Ruby SDK Example

Source: https://docs.llmgateway.io/quick-start

Example of using the Ruby SDK for LLM Gateway integration. Ensure the gem is installed.

```ruby
require "llmgateway"

llm = LLMGateway::Client.new(api_key: ENV["LLM_GATEWAY_API_KEY"])

response = llm.completions.create({
  model: "gpt-3.5-turbo",
  prompt: "Hello world",
})

puts response.choices[0].message.content
```

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

### PHP SDK Example

Source: https://docs.llmgateway.io/quick-start

Example of using the PHP SDK to interact with LLM Gateway. Ensure the SDK is installed via Composer.

```php
<?php

require 'vendor/autoload.php';

use LLMGateway\Client;

$llm = new Client(getenv('LLM_GATEWAY_API_KEY'));

$response = $llm->completions->create([
    'model' => 'gpt-3.5-turbo',
    'prompt' => 'Hello world',
]);

echo $response->choices[0]->message->content;
?>
```

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

### Node.js SDK Example

Source: https://docs.llmgateway.io/quick-start

Example of using the Node.js SDK to interact with LLM Gateway. Ensure the SDK is installed.

```javascript
import LLMGateway from "llmgateway";

const llm = new LLMGateway(process.env.LLM_GATEWAY_API_KEY);

async function main() {
  const response = await llm.completions.create({
    model: "gpt-3.5-turbo",
    prompt: "Hello world",
  });

  console.log(response.choices[0].message.content);
}

main();
```

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

### Install Node.js and pnpm

Source: https://docs.llmgateway.io/guides/agent-skills

Ensure you have Node.js 18+ and pnpm 9+ installed before proceeding with the agent skills setup.

```bash
node --version  # v18.0.0 or higher
pnpm --version  # 9.0.0 or higher
```

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

### Direct LiteLLM Call Example

Source: https://docs.llmgateway.io/migrations/litellm

Example of making a direct call to LiteLLM with specified parameters. Ensure you have the 'litellm' library installed.

```python
import litellm

response = litellm.completion(
    model="gpt-4",
    messages=[
        {"role": "user", "content": "This is a test"}
    ],
    api_key="sk-1234"
)
print(response)
```

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

### Python SDK Example

Source: https://docs.llmgateway.io/quick-start

Example of using the Python SDK to interact with LLM Gateway. Make sure to install the SDK first.

```python
from llmgateway import LLMGateway

llm = LLMGateway(api_key=os.environ.get("LLM_GATEWAY_API_KEY"))

response = llm.completions.create(
    model="gpt-3.5-turbo",
    prompt="Hello world"
)

print(response.choices[0].message.content)
```

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

### Run Hermes Agent Setup Wizard

Source: https://docs.llmgateway.io/guides/hermes-agent

Launch the interactive setup wizard for Hermes Agent. You can choose between a quick setup for basic configuration or a full setup for advanced options.

```bash
hermes setup
```

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

### Tool Use Example

Source: https://docs.llmgateway.io/migrations/litellm

Illustrates how to define and use tools with LiteLLM for more complex interactions. This example shows a tool definition for getting weather information.

```json
{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get the weather for a location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and state, e.g. San Francisco, CA"
                }
            },
            "required": [
                "location"
            ]
        }
    }
}
```

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

### Example Usage of Provider Keys

Source: https://docs.llmgateway.io/learn/provider-keys

This snippet demonstrates how to use provider keys in a typical application flow. Ensure you have the necessary SDKs or libraries installed.

```javascript
self.__next_f.push([
  "37:[\"$\",\"svg\",null,{\"style\":{\"flex\":\"none\",\"lineHeight\":\"1\"},\"fill\":\"currentColor\",\"fillRule\":\"evenodd\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"viewBox\":\"0 0 24 24\",\"children\":[[ \"$\",\"path\",null,{\"d\":\"$6e\"}],[ \"$\",\"path\",null,{\"d\":\"M8.06 10.788c-.003-.038-.004-.075.037-.062.016.006.034.048.028.067-.01.04-.038.032-.064-.005z\"}],[ \"$\",\"path\",null,{\"clipRule\":\"evenodd\",\"d\":\"$6f\"}]]}\]

```

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

### Install OpenCode Desktop on Windows

Source: https://docs.llmgateway.io/guides/opencode-desktop

Download and run the Windows installer for OpenCode Desktop.

```powershell
winget install --id=OpenCode.OpenCode --source winget
```

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

### Docker Compose for Unified Image

Source: https://docs.llmgateway.io/self-host

This snippet shows how to download the Docker Compose file and environment example, configure environment variables, and start the LLM Gateway service using Docker Compose.

```bash
# Download the compose file
curl -O https://raw.githubusercontent.com/theopenco/llmgateway/main/infra/docker-compose.unified.yml
curl -O https://raw.githubusercontent.com/theopenco/llmgateway/main/.env.unified.example

# Configure environment
cp .env.unified.example .env
# Edit .env with your configuration

# Start the service
docker compose -f docker-compose.unified.yml up -d
```

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

### Install Dependencies

Source: https://docs.llmgateway.io/guides/agent-skills

Install all necessary project dependencies using pnpm.

```bash
pnpm install
```

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

### Go SDK Example

Source: https://docs.llmgateway.io/quick-start

Example demonstrating how to use the Go SDK with LLM Gateway. Ensure the SDK is properly imported.

```go
package main

import (
	"fmt"
	"os"

	"github.com/theopenco/llmgateway/go"
)

func main() {
	llm := llmgateway.NewLLMGateway(os.Getenv("LLM_GATEWAY_API_KEY"))

	response, err := llm.Completions.Create(
		"gpt-3.5-turbo",
		"Hello world",
	)

	if err != nil {
		panic(err)
	}

	fmt.Println(response.Choices[0].Message.Content)
}
```

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

### Set up LiteLLM

Source: https://docs.llmgateway.io/migrations/litellm

Initialize LiteLLM with your preferred model and API key. Ensure you have the necessary libraries installed.

```python
from litellm import completion

response = completion(
    model="gpt/3.5-turbo",
    messages=[{"role": "user", "content": "This is a test"}]
)
```

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

### Java SDK Example

Source: https://docs.llmgateway.io/quick-start

Example demonstrating LLM Gateway integration using the Java SDK. Ensure the necessary dependencies are included.

```java
import io.llmgateway.LLMGateway;

public class Main {
    public static void main(String[] args) {
        LLMGateway llm = new LLMGateway(System.getenv("LLM_GATEWAY_API_KEY"));

        String response = llm.completions().create(
            "gpt-3.5-turbo",
            "Hello world"
        );

        System.out.println(response);
    }
}
```

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

### Start Development Server with LLM Gateway CLI

Source: https://docs.llmgateway.io/guides/cli

Navigate to your project directory and run the LLM Gateway CLI to start the development server. This command initializes your AI application.

```bash
cd my-ai-app
npx @llmgateway/cli
```

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

### Initialize LiteLLM Client (After Migration)

Source: https://docs.llmgateway.io/migrations/litellm

Example of initializing the LiteLLM client directly. API keys and base URLs are passed as arguments or set via environment variables.

```python
from litellm import completion

completion(
    model="gpt-3.5-turbo",
    api_key=os.environ.get("OPENAI_API_KEY"),
    base_url="http://localhost:4000/v1"
)

```

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

### Create a Project

Source: https://docs.llmgateway.io/features/master-keys

Use this endpoint to create a new project. Ensure you have your master key for authentication.

```bash
curl -X POST \
  -H "Authorization: Bearer $$MASTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "My New Project",
    "description": "This is a project for testing purposes."
  }' \
  https://internal.llmgateway.io/v1/master/projects
```

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

### Initialize LiteLLM Client (Before Proxy)

Source: https://docs.llmgateway.io/migrations/litellm

Example of initializing the LiteLLM client with base URL and API key from environment variables, as used with the LiteLLM proxy.

```python
from litellm import completion

client = completion(
    model="gpt-3.5-turbo",
    base_url="http://localhost:4000/v1",
    api_key=os.environ["LITELLM_API_KEY"]
)

```

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

### Moderation API Example

Source: https://docs.llmgateway.io/features/moderations

This example demonstrates how to use the moderation API to check for harmful content. Ensure you have the necessary SDKs installed.

```python
from llm_gateway.moderations import Moderations

moderations = Moderations()

async def check_content(text):
    return await moderations.check(text)

async def moderate_content(text):
    return await moderations.moderate(text)
```

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

### Download and Start Unified Docker Compose

Source: https://docs.llmgateway.io/self-host

Use this to quickly set up a single container for LLMGateway. Ensure you configure the .env file with your specific settings.

```bash
curl -O https://raw.githubusercontent.com/theopenco/llmgateway/main/infra/docker-compose.unified.yml
curl -O https://raw.githubusercontent.com/theopenco/llmgateway/main/.env.unified.example

cp .env.unified.example .env
# Edit .env with your configuration

docker compose -f docker-compose.unified.yml up -d
```

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

### AWS Bedrock Embeddings Call Example

Source: https://docs.llmgateway.io/integrations/aws-bedrock

Example of how to get embeddings for a given text using an AWS Bedrock embedding model.

```python
from llmgw.clients import BedrockClient

client = BedrockClient(api_key="YOUR_API_KEY")

response = client.embed(
    model="amazon.titan-embed-text-v1",
    texts=["Hello world", "How are you?"],
)

print(response.embeddings)
```

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

### Python OpenAI SDK Example

Source: https://docs.llmgateway.io/migrations/litellm

Example of updating Python code that uses the OpenAI SDK to work with LiteLLM. Ensure you have the 'openai' library installed.

```python
from openai import OpenAI


```

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

### Initialize a New Project with CLI

Source: https://docs.llmgateway.io/guides/cli

Initialize a new project from a template. Use the --template option to specify a template like 'image-generation' or 'weather-agent'.

```bash
npx @llmgateway/cli init
npx @llmgateway/cli init --template <name>
npx @llmgateway/cli init --template image-generation
npx @llmgateway/cli init --name <name>
npx @llmgateway/cli init --template weather-agent --name my-weather-project
```

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

### Install LLM Gateway Provider

Source: https://docs.llmgateway.io/migrations/vercel-ai-gateway

Install the native LLM Gateway provider for the Vercel AI SDK. This is a necessary step before you can start using LLM Gateway.

```bash
npm install @llm-gateway/vercel-ai-sdk
```

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

### Start LLM Gateway Development Server

Source: https://docs.llmgateway.io/guides/cli

Navigate to your project directory and start the development server. A custom port can be specified.

```bash
cd my-ai-app
npx @llmgateway/cli dev
```

```bash
npx @llmgateway/cli dev --port 3000
```

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

### Retrieve Video Content (Python)

Source: https://docs.llmgateway.io/v1_videos_retrieve

Python code example for retrieving video content. It shows how to make a GET request and process the JSON response.

```python
import requests

response = requests.get("https://example.com/v1/videos/string")
video_data = response.json()
print(video_data)
```

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

### Initialize LiteLLM Client with Direct API Key

Source: https://docs.llmgateway.io/migrations/litellm

Demonstrates initializing the LiteLLM client by directly providing the API key, bypassing environment variables for specific calls.

```python
from litellm import completion

completion(
    model="gpt-3.5-turbo",
    api_key="sk-1234567890",
    base_url="http://localhost:4000/v1"
)

```

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

### MCP Configuration Example

Source: https://docs.llmgateway.io/guides/mcp

This snippet demonstrates a basic configuration structure for MCP, likely for setting up model parameters or network settings.

```text
T4b5,M24 8.4c0 1.325-1.102 2.4-2.462 2.4-1.146 0-2.11-.765-2.384-1.8h-3.436c-.602 0-1.115.424-1.214 1.003l-.101.592a2.38 2.38 0 0 1-.8 1.405c.412.354.704.844.8 1.405l.1.592A1.222 1.222 0 0 0 15.719 15h.975c.273-1.035 1.237-1.8 2.384-1.8 1.36 0 2.461 1.075 2.461 2.4S20.436 18 19.078 18c-1.147 0-2.11-.765-2.384-1.8h-.975c-1.204 0-2.23-.848-2.428-2.005l-.101-.592a1.222 1.222 0 0 0-1.214-1.003H10.97c-.308.984-1.246 1.7-2.356 1.7-1.11 0-2.048-.716-2.355-1.7H4.817c-.308.984-1.246 1.7-2.355 1.7C1.102 14.3 0 13.225 0 11.9s1.102-2.4 2.462-2.4c1.183 0 2.172.815 2.408 1.9h1.337c.236-1.085 1.225-1.9 2.408-1.9 1.184 0 2.172.815 2.408 1.9h.952c.601 0 1.115-.424 1.213-1.003l.102-.592c.198-1.157 1.225-2.005 2.428-2.005h3.436c.274-1.035 1.
```

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

### OpenRouter Migration Guide

Source: https://docs.llmgateway.io/migrations/openrouter

This section outlines the steps and considerations for migrating from OpenRouter to LLM Gateway, including API endpoint mappings and example requests.

```APIDOC
## Migrating from OpenRouter to LLM Gateway

This guide details how to transition your existing OpenRouter integrations to leverage the LLM Gateway API.

### Key Considerations

*   **API Endpoints**: Understand the mapping between OpenRouter's endpoints and LLM Gateway's equivalent endpoints.
*   **Authentication**: Ensure your authentication methods are compatible or updated for LLM Gateway.
*   **Model Names**: Be aware of any differences in model naming conventions.

### Example Migration Steps

This section provides conceptual examples. Please refer to the specific LLM Gateway API documentation for exact request and response formats.

#### 1. Chat Completions

OpenRouter's Chat Completions endpoint can be mapped to LLM Gateway's Chat Completions endpoint.

**OpenRouter Example (Conceptual):**
```http
POST https://openrouter.ai/api/v1/chat/completions
Content-Type: application/json
Authorization: Bearer YOUR_OPENROUTER_API_KEY

{
  "model": "openai/gpt-3.5-turbo",
  "messages": [
    {"role": "user", "content": "Hello!"
    }
  ]
}
```

**LLM Gateway Equivalent (Conceptual):
**
```http
POST https://api.llmgateway.io/v1/chat/completions
Content-Type: application/json
Authorization: Bearer YOUR_LLMGATEWAY_API_KEY

{
  "model": "openai/gpt-3.5-turbo",
  "messages": [
    {"role": "user", "content": "Hello!"
    }
  ]
}
```

### 2. Model Listing

Migrating from fetching models via OpenRouter to LLM Gateway.

**OpenRouter Example (Conceptual):**
```http
GET https://openrouter.ai/api/v1/models
Authorization: Bearer YOUR_OPENROUTER_API_KEY
```

**LLM Gateway Equivalent (Conceptual):**
```http
GET https://api.llmgateway.io/v1/models
Authorization: Bearer YOUR_LLMGATEWAY_API_KEY
```

### Further Assistance

For detailed API specifications, refer to the official LLM Gateway API documentation.
```

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

### Retrieve Video Content (Python)

Source: https://docs.llmgateway.io/v1_videos_content

Python code to stream video content. This example demonstrates making a GET request and saving the response body as a file.

```python
import requests

url = "https://llmgateway.io/v1/videos/content?id=..."
api_key = "YOUR_API_KEY"

headers = {
    "accept": "application/octet-stream",
    "Authorization": f"Bearer {api_key}"
}

response = requests.get(url, headers=headers, stream=True)

if response.status_code == 200:
    with open("output.mp4", "wb") as f:
        for chunk in response.iter_content(chunk_size=8192):
            f.write(chunk)
    print("Video saved to output.mp4")
else:
    print(f"Error: {response.status_code}")
    print(response.text)
```

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

### Create a Project with Master Key

Source: https://docs.llmgateway.io/features/master-keys

Use this endpoint to create a new project. Provide the project name, and optionally enable caching and set a cache duration. The mode can be 'api-keys', 'credits', or 'hybrid'.

```bash
curl -X POST https://api.llmgateway.ai/v1/master/projects \
  -H "Authorization: Bearer YOUR_MASTER_KEY" \
  -d '{
    "name": "Customer ACME",
    "cachingEnabled": false,
    "mode": "hybrid"
}'
```

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

### Retrieve Video Content (C#)

Source: https://docs.llmgateway.io/v1_videos_content

C# example for fetching video content from the LLM Gateway API. This uses the HttpClient class to perform a GET request.

```csharp
using System;
using System.Net.Http;
using System.Threading.Tasks;

public class VideoFetcher {
    public static async Task GetVideoContent() {
        using (HttpClient client = new HttpClient()) {
            string url = "https://example.com/v1/videos/string/content";
            HttpResponseMessage response = await client.GetAsync(url);

            if (response.IsSuccessStatusCode) {
                string content = await response.Content.ReadAsStringAsync();
                Console.WriteLine("Success!");
                // Process content
            } else {
                Console.WriteLine($"Error: {response.StatusCode}");
            }
        }
    }
}
```

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

### Initialize a new LLM Gateway project

Source: https://docs.llmgateway.io/guides/cli

Use the 'init' command to scaffold a new LLM Gateway project. This sets up the basic project structure and configuration files.

```bash
npx @llmgateway/cli init
```

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

### Retrieve Video Content (JavaScript)

Source: https://docs.llmgateway.io/v1_videos_content

Example of retrieving video content using JavaScript. This snippet demonstrates a basic GET request to the LLM Gateway API.

```javascript
fetch("https://example.com/v1/videos/string/content", {
  method: "GET"
}).then(response => {
  // Handle response
});
```

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

### Create Project

Source: https://docs.llmgateway.io/features/master-keys

Create a new project within the master key's organization. Specify the project name and optional caching configurations.

```bash
curl -X POST https://internal.llmgateway.io/v1/master/projects \
  -H "Authorization: Bearer $MASTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Customer ACME",
    "cachingEnabled": false,
    "mode": "hybrid"
  }'
```

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

### Send a Request with System Prompt via CLI

Source: https://docs.llmgateway.io/guides/cline

This example demonstrates sending a request that includes a system prompt, which helps guide the model's behavior.

```bash
llmcli send --model "gpt-4" --prompt "Write a short poem about the sea." --system-prompt "You are a helpful assistant that writes poetry."
```

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

### Migrate OpenAI Client Initialization

Source: https://docs.llmgateway.io/migrations/litellm

Shows how to initialize the OpenAI client using LiteLLM's proxy before and after migration. This example demonstrates the change in client initialization when switching from direct OpenAI SDK usage to LiteLLM's proxy.

```typescript
import OpenAI

// Before (LiteLLM proxy)
const client = new OpenAI({
	baseURL: "http://localhost:8000",
});

// After (LiteLLM proxy)
const client = new OpenAI({
	baseURL: "http://localhost:8000",
});
```

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

### Create Chat Completion with OpenAI Model

Source: https://docs.llmgateway.io/migrations/litellm

Example of how to create a chat completion using the LiteLLM client with an OpenAI model. Ensure you have the LiteLLM client installed and configured.

```python
import litellm

response = litellm.completion(
    model="openai/gpt-4",
    messages=[
        {"role": "user", "content": "What's the weather in Tokyo?"}
    ]
)
```

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

### LLM Gateway Call with Different Model

Source: https://docs.llmgateway.io/migrations/litellm

Shows how to use LLM Gateway to call the 'claude-3-sonnet-20240229' model. The setup is similar to the previous example, only changing the model name.

```python
from openai import OpenAI

client = OpenAI(
    base_url="https://llm.llmgateway.io",
    api_key="sk-ant-..."
)

response = client.chat.completions.create(
    model="claude-3-sonnet-20240229",
    messages=[
        {"role": "user", "content": "This is a test"}
    ]
)
print(response)
```

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

### LLMGateway CLI Example

Source: https://docs.llmgateway.io/guides/cline

This snippet demonstrates a basic command for interacting with the LLMGateway CLI. It's useful for initiating requests or checking service status.

```bash
self.__next_f.push([1,"6c:T7c2," ])
self.__next_f.push([1,"m142.27 316.619 73.655-41.326 1.238-3.589-1.238-1.996-3.589-.001-12.31-.759-42.084-1.138-36.498-1.516-35.361-1.896-8.897-1.895-8.34-10.995.859-5.484 7.482-5.03 10.717.935 23.683 1.617 35.537 2.452 25.782 1.517 38.193 3.968h6.064l.86-2.451-2.073-1.517-1.618-1.517-36.776-24.922-39.81-26.338-20.852-15.166-11.273-7.683-5.687-7.204-2.451-15.721 10.237-11.273 13.75.935 3.513.936 13.928 10.716 29.749 23.027 38.848 28.612 5.687 4.727 2.275-1.617.278-1.138-2.553-4.271-21.13-38.193-22.546-38.848-10.035-16.101-2.654-9.655c-.935-3.968-1.617-7.304-1.617-11.374l11.652-15.823 6.445-2.073 15.545 2.073 6.547 5.687 9.655 22.092 15.646 34.78 24.265 47.291 7.103 14.028 3.791 12.992 1.416 3.968 2.449-.001v-2.275l1.997-26.641 3.69-32.707 3.589-42.084 1.239-11.854 5.863-14.206 11.652-7.683 9.099 4.348 7.482 10.716-1.036 6.926-4.449 28.915-8.72 45.294-5.687 30.331h3.313l3.792-3.791 15.342-20.372 25.782-32.227 11.374-12.789 13.27-14.129 8.517-6.724 16.1-.001 11.854 17.617-5.307 18.199-16.581 21.029-13.75 17.819-19.716 26.54-12.309 21.231 1.138 1.694 2.932-.278 44.536-9.479 24.062-4.347 28.714-4.928 12.992 6.066 1.416 6.167-5.106 12.613-30.71 7.583-36.018 7.204-53.636 12.689-.657.48.758.935 24.164 2.275 10.337.556h25.301l47.114 3.514 12.309 8.139 7.381 9.959-1.238 7.583-18.957 9.655-25.579-6.066-59.702-14.205-20.474-5.106-2.83-.001v1.694l17.061 16.682 31.266 28.233 39.152 36.397 1.997 8.999-5.03 7.102-5.307-.758-34.401-25.883-13.27-11.651-30.053-25.302-1.996-.001v2.654l6.926 10.136 36.574 54.975 1.895 16.859-2.653 5.485-9.479 3.311-10.414-1.895-21.408-30.054-22.092-33.844-17.819-30.331-2.173 1.238-10.515 113.261-4.929 5.788-11.374 4.348-9.478-7.204-5.03-11.652 5.03-23.027 6.066-30.052 4.928-23.886 4.449-29.674 2.654-9.858-.177-.657-2.173.278-22.37 30.71-34.021 45.977-26.919 28.815-6.445 2.553-11.173-5.789 1.037-10.337 6.243-9.2 37.257-47.392 22.47-29.371 14.508-16.961-.101-2.451h-.859l-98.954 64.251-17.618 2.275-7.583-7.103.936-11.652 3.589-3.791 29.749-20.474-.101.102.024.101z"]

```

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

### Configure LLM Gateway API Key

Source: https://docs.llmgateway.io/guides/hermes-agent

Paste your LLM Gateway API key when prompted by the Hermes Agent setup wizard. The key typically starts with 'llmgtwy_'.

```bash
API key: llmgtwy_...
```

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

### Retrieve Video Content (Go)

Source: https://docs.llmgateway.io/v1_videos_content

A Go program to fetch video content from the LLM Gateway API. This example shows how to make a GET request and handle the response.

```go
package main

import (
	"fmt"
	"net/http"
)

func main() {
	resp, err := http.Get("https://example.com/v1/videos/string/content")
	if err != nil {
		fmt.Println("Error making request:", err)
		return
	}
	defer resp.Body.Close()

	// Process response body
	fmt.Println("Status Code:", resp.StatusCode)
}
```

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

### Chat Completion Request (Node.js)

Source: https://docs.llmgateway.io/v1_chat_completions

An example of making a chat completion request using the OpenAI Node.js library. Make sure to install the library and set up your API key.

```javascript
import OpenAI from 'openai';

const openai = new OpenAI();

async function main() {
  const completion = await openai.chat.completions.create({
    model: "gpt-3.5-turbo",
    messages: [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
  });

  console.log(completion.choices[0].message.content);
}

main();
```

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

### LLM Gateway Client Initialization

Source: https://docs.llmgateway.io/migrations/openrouter

This example demonstrates the initialization of a client for the LLM Gateway, which is a common pattern when integrating with various LLM providers through a unified interface.

```javascript
const client = new LLM(
  // LLM Gateway provider configuration
  {
    provider: "openrouter",
    provider_options: {
      api_key: process.env.OPENROUTER_API_KEY,
    },
  }
);
```

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

### Initialize LLM Gateway SDK

Source: https://docs.llmgateway.io/migrations/openrouter

Set up the LLM Gateway SDK by providing your API key. Ensure the LLMGATEWAY_API_KEY environment variable is set.

```javascript
const llmgateway = require("@llmgateway/ai-sdk-provider");

const { createLLMGateway } = llmgateway;

const { LLMGATEWAY_API_KEY } = process.env;
```

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

### LLM Gateway with System Message

Source: https://docs.llmgateway.io/self-host

This example demonstrates including a system message in the conversation to guide the LLM's behavior. System messages set the context or persona for the AI.

```python
import requests

url = "http://localhost:8000/v1/chat/completions"
headers = {
    "Content-Type": "application/json"
}
data = {
    "model": "default",
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Who won the world series in 2020?"}
    ]
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

```