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

# What is Kyma API?

> LLM API gateway — active models, one endpoint, built-in redundancy.

## Overview

Kyma API gives you instant access to the best open source LLMs through a single endpoint. Compatible with both **OpenAI** and **Anthropic** SDKs. Multi-provider redundancy means your requests always go through — even when individual providers are down.

<CardGroup cols={3}>
  <Card title="75 models, one endpoint" icon="robot">
    Qwen 3.6, DeepSeek V4, Gemma 4, GPT-OSS, Kimi K2.6, Gemini, Llama, MiniMax, GLM, Perplexity Sonar for live web search, plus GPT Image 2, FLUX, Ideogram, Recraft, MiniMax Image for image generation, Kling, Seedance, Hailuo for video, ElevenLabs and MiniMax for voice and music.
  </Card>

  <Card title="Auto-Failover" icon="shield-check">
    Multi-provider redundancy. If one fails, your request is automatically retried on another.
  </Card>

  <Card title="OpenAI Compatible" icon="plug">
    Drop-in replacement. Works with any OpenAI SDK, LangChain, Cursor, and more.
  </Card>
</CardGroup>

## Why Kyma?

|                | Kyma                  | Other gateways  | Direct API     |
| -------------- | --------------------- | --------------- | -------------- |
| **Price**      | \$0.50 free credit    | \$0.001+/token  | Free (limited) |
| **Models**     | Curated active models | 200+ (paid)     | 1 per provider |
| **Redundancy** | Auto-failover         | Single provider | None           |
| **Setup time** | 30 seconds            | 5 minutes       | Per-API signup |
| **OpenAI SDK** | ✅                     | ✅               | ✅              |

## How it works

```
Your App → Kyma API → Best available infrastructure
                    ↳ Auto-failover if primary is down
                    ↳ Same model on backup, or equivalent quality
```

Kyma automatically routes your request to the fastest available infrastructure. If a provider is down, your request is silently retried on another — you never see an error. No need to manage multiple API keys or monitor provider status.

## Quick example

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

  client = OpenAI(
      base_url="https://kymaapi.com/v1",
      api_key="YOUR_KEY"
  )

  response = client.chat.completions.create(
      model="llama-3.3-70b",
      messages=[{"role": "user", "content": "Hello!"}]
  )
  print(response.choices[0].message.content)
  ```

  ```javascript JavaScript theme={null}
  import OpenAI from "openai";

  const client = new OpenAI({
    baseURL: "https://kymaapi.com/v1",
    apiKey: "YOUR_KEY",
  });

  const response = await client.chat.completions.create({
    model: "llama-3.3-70b",
    messages: [{ role: "user", content: "Hello!" }],
  });
  console.log(response.choices[0].message.content);
  ```

  ```bash cURL theme={null}
  curl https://kymaapi.com/v1/chat/completions \
    -H "Authorization: Bearer YOUR_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "llama-3.3-70b",
      "messages": [{"role": "user", "content": "Hello!"}]
    }'
  ```
</CodeGroup>

<Card title="Ready to start?" icon="rocket" href="/quickstart">
  Get your API key and make your first request in 30 seconds →
</Card>