> ## 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.

# Cursor IDE

> Use Kyma API as your AI backend in Cursor.

## Setup

<Steps>
  <Step title="Open Cursor Settings">
    `Cmd+,` (Mac) or `Ctrl+,` (Windows) → search "OpenAI"
  </Step>

  <Step title="Configure API">
    Set the following:

    * **OpenAI API Key**: `ky-your-api-key`
    * **API Base URL**: `https://kymaapi.com/v1`
  </Step>

  <Step title="Select model">
    Add custom model: `llama-3.3-70b` or `qwen-3-32b`
  </Step>

  <Step title="Start coding">
    Use `Cmd+K` to chat with AI using Kyma's models.
  </Step>
</Steps>

## Recommended models for Cursor

| Model               | Alias          | Best For                                                              |
| ------------------- | -------------- | --------------------------------------------------------------------- |
| `qwen-3.6-plus`     | `best`         | **Recommended** — highest quality overall                             |
| `qwen-3-coder`      | `code`         | Best alias for code-focused tasks                                     |
| `kimi-k2.6`         | `agent`        | Best tool calling, agentic workflows                                  |
| `gemini-2.5-flash`  | `long-context` | 1M context for large codebases                                        |
| `deepseek-v4-pro`   | —              | 1M context, top reasoning. Complex refactors and long-codebase tasks. |
| `deepseek-v4-flash` | —              | 1M context, value tier. Everyday completions where speed matters.     |

<Tip>
  Use [model aliases](/guides/model-aliases) like `best` or `code` — they auto-update when better models become available.
</Tip>

```bash theme={null}
curl "https://kymaapi.com/v1/models/recommend?agent=cursor"
```

## Audio Models (optional)

Cursor is a coding IDE first, but if you bolt audio tooling onto your workflow (voice notes, meeting recap macros, audio QA fixtures), Kyma's audio aliases work the same as any chat model:

* `transcribe` → `whisper-v3-turbo` — 228× realtime speech-to-text
* `audio-understand` → `gemini-3-flash-audio` — scene/tone/music recognition

Use them via `POST /v1/audio/transcriptions` and `POST /v1/audio/understand`. The full audio surface (TTS, music, SFX, voice clone/design) is documented in the [Audio API reference](/api-reference/audio-speech) and [Model Aliases](/guides/model-aliases#audio-aliases).

## Prompt Caching

Prompt caching is automatic. Your system prompt and tool definitions are cached for 5 minutes, reducing costs by up to 90% on subsequent requests. No code changes needed. See [Prompt Caching](/guides/prompt-caching) for details.