> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.ortavox.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.ortavox.ai/_mcp/server.

# Model Configurations

> Configure the AI model powering your Ortavox Agent

The `model` object in your Agent configuration defines which language model processes the conversation. It is a **required** field when creating or updating an Agent.

## Schema

```json
{
  "model": {
    "provider": "openai",
    "model": "gpt-4o-mini",
    "system_prompt": "You are a helpful AI assistant.",
    "temperature": 0.8,
    "max_tokens": 3500,
    "tools": []
  }
}
```

## Parameters

| Property        | Type     | Required | Description                                            |
| --------------- | -------- | -------- | ------------------------------------------------------ |
| `provider`      | `string` | ✅        | LLM provider (see supported providers below)           |
| `model`         | `string` | ✅        | Model ID from the provider (e.g. `gpt-4o-mini`)        |
| `system_prompt` | `string` | ✅        | The system instruction given to the model              |
| `temperature`   | `number` | ✅        | Randomness level — `0.0` to `2.0`, default `0.8`       |
| `max_tokens`    | `number` | ✅        | Max tokens per response, default `3500`                |
| `tools`         | `array`  | ❌        | List of tool IDs to attach to this model, default `[]` |

## Supported Providers

| Provider      | `provider` value |
| ------------- | ---------------- |
| OpenAI        | `openai`         |
| Anthropic     | `anthropic`      |
| Google Gemini | `google`         |
| Groq          | `groq`           |
| DeepSeek      | `deep-seek`      |