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

# Samurai AI

> Access 400+ AI models through a single OpenAI-compatible API — at 50% off provider prices.

<Info>
  **One API, Unlimited Possibilities**: Access GPT-4.1, Claude Opus 4, Gemini 2.5 Pro, and 400+ models without juggling multiple providers.
</Info>

## What is Samurai AI?

Samurai AI is your **"super-API"** for AI. Instead of integrating with OpenAI, Anthropic, Google, and other providers separately, you get access to all their models through one unified interface — at **50% of the original provider price**.

### Why Samurai AI?

* **50% Cheaper**: Pay half the provider price on every model, every time
* **Instant Model Switching**: Change models with one parameter — no code rewrites
* **OpenAI Compatible**: Drop-in replacement — just change `base_url` and go
* **400+ Models**: Chat, audio, embeddings — all in one API
* **Unified Billing**: One invoice for all your AI usage

## Quick Start

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket-launch" href="/quickstart">
    Get your API key and make your first request in minutes.
  </Card>

  <Card title="Authentication" icon="shield-halved" href="/authentication">
    Get your API key and start building.
  </Card>

  <Card title="Browse Models" icon="grid-2-plus" href="/reference/models">
    GPT-4.1, Claude Opus 4, Gemini 2.5 Pro, and 400+ more.
  </Card>

  <Card title="API Playground" icon="flask" href="/api-reference/introduction">
    Test every endpoint live in your browser.
  </Card>
</CardGroup>

## Core Features

<CardGroup cols={3}>
  <Card title="50% Cheaper" icon="tag" href="/reference/pricing">
    `gpt-4o` for \*\*$1.25/1M tokens** vs $2.50 direct. `claude-3-5-sonnet` for \*\*$1.50/1M** vs $3.00. Every model, every time.
  </Card>

  <Card title="OpenAI Compatible" icon="plug" href="/api/chat-completions">
    Change `base_url` and your API key. SDKs, streaming, function calling, vision — all work exactly the same.
  </Card>

  <Card title="400+ Models" icon="microchip" href="/reference/models">
    Chat, audio, embeddings — all in one API. New models added as they launch from providers.
  </Card>
</CardGroup>

## Base URL

```
https://www.samuraiapi.in/v1
```

That's the only change you need from OpenAI. Your existing code works as-is.

## Who Uses Samurai AI?

### Developers

* Experiment with 400+ models without rewriting code
* Reduce integration complexity from weeks to minutes
* Build faster with one API key, one SDK, one invoice

### Businesses

* Cut AI costs by 50% immediately across every model
* Ensure high availability for customer-facing AI features
* Future-proof AI investments with provider flexibility

### Researchers

* Access cutting-edge models as they're released
* Run evaluations across GPT, Claude, Gemini, and more from one endpoint
* Test model performance across different tasks without managing multiple accounts

## Example: Switching Models

<CodeGroup>
  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(
      base_url="https://www.samuraiapi.in/v1",
      api_key="sk-samurai-YOUR_KEY"
  )

  # Use GPT-4.1 for complex reasoning
  response = client.chat.completions.create(
      model="gpt-4.1",
      messages=[{"role": "user", "content": "Analyze this data..."}]
  )

  # Switch to Claude Opus for creative writing
  response = client.chat.completions.create(
      model="claude-opus-4-5",
      messages=[{"role": "user", "content": "Write a story about..."}]
  )

  # Use Gemini for large context tasks
  response = client.chat.completions.create(
      model="gemini-2.5-pro",
      messages=[{"role": "user", "content": "Summarize this document..."}]
  )
  ```

  ```javascript Node.js theme={null}
  import OpenAI from "openai";

  const client = new OpenAI({
    apiKey: "sk-samurai-YOUR_KEY",
    baseURL: "https://www.samuraiapi.in/v1",
  });

  // GPT-4.1 for reasoning
  const r1 = await client.chat.completions.create({
    model: "gpt-4.1",
    messages: [{ role: "user", content: "Analyze this data..." }],
  });

  // Claude Opus for creative writing
  const r2 = await client.chat.completions.create({
    model: "claude-opus-4-5",
    messages: [{ role: "user", content: "Write a story about..." }],
  });
  ```
</CodeGroup>

## Popular Model Combinations

| Use Case             | Primary Model            | Why                  |
| -------------------- | ------------------------ | -------------------- |
| **Chatbots**         | `gpt-4o-mini`            | Fast, cost-effective |
| **Code Generation**  | `gpt-4.1`                | Best code quality    |
| **Complex Analysis** | `claude-opus-4-5`        | Superior reasoning   |
| **Creative Writing** | `claude-opus-4-5`        | Creative excellence  |
| **Large Context**    | `gemini-2.5-pro`         | 1M+ token context    |
| **Embeddings**       | `text-embedding-3-small` | Fast, cheap vectors  |

## Getting Started

<Tip>
  **Ready to go?** Make your first API call in under 5 minutes.
</Tip>

<Steps>
  <Step title="Get API Key">
    [Sign up](https://www.samuraiapi.in/register) for a Samurai AI account and get your API key from the dashboard.
  </Step>

  <Step title="Install SDK">
    Use the OpenAI SDK you already know — no new packages needed.

    ```bash theme={null}
    pip install openai
    # or
    npm install openai
    ```
  </Step>

  <Step title="Make Your First Request">
    Point to Samurai AI and start using any of 400+ models.

    ```python theme={null}
    from openai import OpenAI

    client = OpenAI(
        api_key="sk-samurai-YOUR_KEY",
        base_url="https://www.samuraiapi.in/v1"
    )

    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": "Hello!"}]
    )
    print(response.choices[0].message.content)
    ```
  </Step>
</Steps>

## Need Help?

* **Browse our guides**: Comprehensive documentation for every feature
* **Check the FAQ**: [Common questions and answers](/reference/faq)
* **Contact support**: [support@samuraiapi.in](mailto:support@samuraiapi.in) for technical assistance
* **Discord**: [Join our community](https://discord.gg/7TsWbcK2j)
* **Use search**: Press `Cmd+K` / `Ctrl+K` to search all documentation