> ## Documentation Index
> Fetch the complete documentation index at: https://hastekit.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Get up and running with HasteKit LLM Gateway in minutes.

## Prerequisites

* [Docker](https://www.docker.com/products/docker-desktop/) and Docker Compose.

## 1. Start HasteKit LLM Gateway

Start HasteKit gateway with a single command:

```bash theme={null}
npx @hastekit/ai-gateway
```

This command will automatically download the required files and start all services.

### Optional: Start with Additional Services

You can also start HasteKit gateway with additional worker services:

```bash theme={null}
# Start with Temporal worker
npx @hastekit/ai-gateway --temporal

# Start with Restate service
npx @hastekit/ai-gateway --restate

# Start with both Temporal and Restate
npx @hastekit/ai-gateway --all
```

## 2. Open the Dashboard

Once the services are running, open `http://localhost:3000` in your browser.

## 3. Configure a Provider

1. Navigate to the **Providers** tab in the Dashboard.
2. Choose one of the supported providers from the sidebar.
3. Click **Add API Key** and enter your provider API Key and click **Create**.
4. Go to **Virtual Keys** and create a new key for your project. Note down the key.

## 4. Point your SDK to the LLM Gateway

Now, update your application to send LLM calls to the gateway and use the virtual key instead of the provider's API key.

<CodeGroup dropdown>
  ```go main.go theme={null}
  package main

  import (
      "context"
      "fmt"

      "github.com/openai/openai-go/v3"
      "github.com/openai/openai-go/v3/option"
      "github.com/openai/openai-go/v3/shared"
  )

  func main() {
      client := openai.NewClient(
          option.WithBaseURL("http://localhost:6060/api/gateway/openai")
          option.WithAPIKey("your-virtual-key--or--provider-api-key"),
      )

      chatCompletion, err := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
          Model: openai.ChatModelGPT4_1Mini,
          Instructions: "You are a coding assistant that talks like a pirate.",
          Messages: []openai.ChatCompletionMessageParamUnion{
              openai.UserMessage("Hello!"),
          },
      })

      if err != nil {
          panic(err.Error())
      }

      println(chatCompletion.Choices[0].Message.Content)
  }
  ```

  ```python main.py theme={null}
  import os
  from openai import OpenAI

  client = OpenAI(
      base_url="http://localhost:6060/api/gateway/openai",
      api_key="your-virtual-key--or--provider-api-key",
  )

  response = client.responses.create(
      model="gpt-4.1-mini",
      instructions="You are a coding assistant that talks like a pirate.",
      input="Hello!",
  )

  print(response.output_text)
  ```
</CodeGroup>