> For the complete documentation index, see [llms.txt](https://ai.ortusbooks.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai.ortusbooks.com/main-components/profiles.md).

# Profiles

Name a provider, model, params and key once, then select it by name.

A profile is a named combination of provider, model, params, options and API key. Define `fast` and `planner` once, then pick one per call, per agent, or per run. Without profiles, nothing changes.

## 🛠️ Define

In `boxlang.json`:

```json
{
  "modules": { "bxai": { "settings": {
    "provider": "openai",
    "profiles": {
      "fast": {
        "description": "Cheap and quick, for small tasks",
        "provider": "openai",
        "model": "gpt-4.1-mini",
        "params": { "temperature": 0 },
        "apiKeyEnv": "OPENAI_API_KEY"
      },
      "planner": {
        "description": "Slower and smarter, for planning",
        "provider": "claude",
        "model": "claude-opus-5-5",
        "params": { "temperature": 0.7, "max_tokens": 8192 },
        "apiKeyEnv": "CLAUDE_API_KEY"
      }
    },
    "defaultProfile": ""
  } } }
}
```

| Key           | Meaning                                                                    |
| ------------- | -------------------------------------------------------------------------- |
| `description` | Free text for people and UIs. Returned by `aiProfile()` and `aiProfiles()` |
| `provider`    | Provider key. Empty uses the top level `provider`                          |
| `model`       | Shorthand for `params.model`                                               |
| `params`      | Request params for this profile                                            |
| `options`     | Request options for this profile, such as `timeout`                        |
| `apiKeyEnv`   | The **name** of the environment variable that holds the key. Preferred     |
| `apiKey`      | A literal key. Avoid it                                                    |

The profile `default` always exists. It is your top level `provider`, `apiKey` and `defaultParams`. Set `defaultProfile` to make another profile the one used when a call names no provider.

**Rules**, checked when the module starts: a profile cannot be named like a provider (`openai`, `claude`, ...) or `default`, names use letters, numbers, `_` and `-`, and `defaultProfile` must exist. A broken setting throws `InvalidConfiguration`.

## 🎯 Use

```javascript
// Chat and embeddings: options.profile
aiChat( "Summarize this", {}, { profile: "fast" } )
aiChatStream( "Tell a story", chunk => print( chunk ), {}, { profile: "fast" } )
aiEmbed( "Hello", {}, { profile: "embed" } )

// Services, models and agents: the profile argument
service = aiService( profile: "planner" )
model   = aiModel( profile: "fast" )
agent   = aiAgent( name: "support", profile: "fast" )
```

An explicit provider, key, param or option in the call always wins. Params layer from lowest to highest: `defaultParams`, `providers.<name>.params`, the profile, the call. An unknown profile throws `ProfileNotFound`.

{% hint style="info" %}
Pass either `model` or `profile` to `aiAgent()`, not both.
{% endhint %}

{% hint style="info" %}
Profiles cover chat, streaming and embeddings. Audio (`aiSpeak()`, `aiTranscribe()`, `aiTranslate()`) and images (`aiImage()`) keep using the `audio` and `image` settings.
{% endhint %}

## 🔀 Switch an agent

```javascript
// One run only: the agent keeps its own profile, memory is shared
agent.run( "Plan the migration", {}, { profile: "planner" } )

// For good: replaces the model, keeps memory, tools, sub-agents, params and options
agent.withProfile( "planner" )
agent.getProfile() // "planner"
```

The middleware, skills and MCP servers of the agent's model also stay. `agent.setModel( model )` sets the profile to the one the new model was built from, or empty when it has none.

`stream()` takes the same `profile` option. To give a sub-agent its own profile, create it with one: `aiAgent( name: "researcher", profile: "planner" )`, then pass it in `subAgents`.

## 📋 List

Built for chat UIs and remote control, such as `/profile` and `/provider` commands:

```javascript
aiProfiles()        // all profiles, the default first
aiProfile( "fast" ) // one profile
aiProviders()       // the providers you can pick
```

See [aiProfiles](/advanced/reference/built-in-functions/aiprofiles.md), [aiProfile](/advanced/reference/built-in-functions/aiprofile.md) and [aiProviders](/advanced/reference/built-in-functions/aiproviders.md).

## 🔐 Keys stay secret

* Use `apiKeyEnv`. The key is read from the environment when the profile is used.
* Listings return `hasApiKey` and the variable name, never the key. Params and options that look like secrets (`key`, `token`, `secret`, `password`) show as `****`.
* A profile key is only sent to the profile's own provider. The same goes for its params (including its model) and options: `aiChat( "Hi", {}, { profile: "fast", provider: "claude" } )` sends none of them to Claude.
* Profiles are never copied into request options, so they do not reach logs or events.

## 📡 Event

`onAIProfileSwitch` fires when an agent changes profile. See [events](/advanced/events.md#70-onaiprofileswitch).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://ai.ortusbooks.com/main-components/profiles.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.