> ## 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.

# Roo Code

> Use Kyma with Roo Code VS Code extension.

Roo Code is an AI dev team in your IDE. Configure Kyma as an OpenAI Compatible provider.

## Setup

1. Open Roo Code settings in VS Code
2. Select **"OpenAI Compatible"** as the provider
3. Fill in:

| Field | Value |
| - | - |
| **Base URL** | `https://kymaapi.com/v1` |
| **API Key** | Your `kyma-` key |
| **Model ID** | `qwen-3.6-plus` |

## Recommended Models

| Model | Best For | Free tier |
| - | - | - |
| `qwen-3.6-plus` | **Recommended** — highest quality, #1 on Kyma | Yes |
| `qwen-3-coder` | Best for code-focused tasks | Yes |
| `kimi-k2.6` | Best tool calling, 262K context | No, needs a top-up |
| `llama-3.3-70b` | Great all-rounder | Yes |
| `deepseek-v4-flash` | 1M context, value tier. Everyday completions where speed matters. | Yes |

> [!NOTE]
>
> A new account's signup credit is added once your email is verified and spends on [free tier](https://docs.kymaapi.com/pricing.md#free-tier) models only. Models outside it return `402 model_requires_paid` until your first top-up.

```bash theme={null}
# Get personalized recommendation
curl "https://kymaapi.com/v1/models/recommend?agent=roo-code"
```

Call an exact model id; see [Model Aliases](https://docs.kymaapi.com/guides/model-aliases.md) for how old alias names are handled.

## Audio Models (optional)

Roo Code is a coding agent, but if you build voice-enabled extensions or transcript pipelines on the side, Kyma's audio models drop in like any chat model:

* `whisper-v3-turbo` — 228× realtime speech-to-text

Use them via `POST /v1/audio/transcriptions`. Text-to-speech is documented in the [Audio API reference](https://docs.kymaapi.com/api-reference/audio-speech.md) and [Model Aliases](https://docs.kymaapi.com/guides/model-aliases.md).

## Prompt Caching

Some models cache a repeated prompt prefix. `pricing.cached` on [`/v1/models`](https://kymaapi.com/v1/models) is the rate Kyma publishes for cached input on that model — usually below its input rate, but not always, so compare the two for the model you use. Every chat completion reports `usage.cost`, what the request was charged, and `usage.cache_discount`, Kyma's figure for what caching saved on it. Whether a prefix is cached automatically or needs a `cache_control` marker depends on the model's creator. See [Prompt Caching](https://docs.kymaapi.com/guides/prompt-caching.md) for details.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.