# CARTO AI

CARTO AI adds AI capabilities across the CARTO platform. This includes [AI Agents](https://app.gitbook.com/o/zP3LT2Qhlb5jPWQCfWV3/s/ybPdpmLltPkzGFvz7m8A/~/changes/1466/carto-user-manual/ai-agents) in Builder for natural-language interaction with maps, along with other AI features where supported.

## Enabling CARTO AI

To enable AI capabilities in your platform, navigate to CARTO AI section within your organization's setting and toggle **Enable CARTO AI**.

<figure><img src="https://3029946802-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FybPdpmLltPkzGFvz7m8A%2Fuploads%2FE2TftTv3F74twhmzO6vE%2FScreenshot%202026-03-19%20at%2016.57.40.png?alt=media&#x26;token=8b8e8788-b2d9-4ae5-83c9-d4544ad40282" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
By enabling CARTO AI, you agree to the [CARTO AI terms and conditions.](https://drive.google.com/file/d/1QqidTLrDNqMbWg0D1RbHC3lkOSOHVXam/view?usp=drive_link)
{% endhint %}

## Default Model

Once CARTO AI is enabled, you can select a default model that will be used across all CARTO AI features. This model is automatically applied when using or configuring AI-powered capabilities.

To set the default model:

* Navigate to Settings > CARTO AI
* Ensure CARTO AI is enabled
* Use the Default model dropdown to select your preferred model

You can change the default model at any time. The available models in the dropdown include either CARTO-managed models or any custom models you've configured from your own AI providers.&#x20;

{% hint style="info" %}
The default model is pre-selected when configuring or using AI-powered features. However, Editor users can override this selection and choose a different model as needed.
{% endhint %}

## Model Options

### CARTO managed models (default)

When you enable CARTO AI, these models are available immediately:

* **claude-opus-4.6:** Recommended default for geospatial use cases across CARTO AI. Best-in-class reasoning, spatial analysis, SQL generation, and high-accuracy insights.
* **claude-sonnet-4-6**: High-performance model with strong reasoning capabilities. Good balance of quality and efficiency.
* **gemini-3-pro**: Advanced Gemini model with strong geospatial reasoning and multi-modal capabilities.
* **gemini-3-flash**: Fast and efficient Gemini model, ideal for simpler queries and high-volume interactions.

### Bring your own model

Organizations can configure their own AI models from multiple providers, giving you full control over model selection, data residency, and cost management.&#x20;

#### Supported Providers

<table><thead><tr><th width="195.63671875">Provider</th><th width="222.140625">Authentication</th><th>Supported Models</th></tr></thead><tbody><tr><td><a href="#google-vertex-ai">Google Vertex AI</a></td><td>Service Account</td><td><code>gemini-3-pro</code>, <code>gemini-3-flash</code>, <code>gemini-2.5-pro</code>, <code>gemini-2.5-flash</code>, <code>claude-opus-4.6</code>, <code>claude-sonnet-4.6</code>, <code>claude-opus-4.5</code>, <code>claude-sonnet-4.5</code></td></tr><tr><td><a href="#google-ai-studio">Google AI Studio</a></td><td>API Key</td><td><code>gemini-3-pro</code>, <code>gemini-3-flash</code>, <code>gemini-2.5-pro</code>, <code>gemini-2.5-flash</code></td></tr><tr><td><a href="#openai">OpenAI</a></td><td>API Key</td><td><code>gpt-5.2-pro</code>, <code>gpt-5.2</code>, <code>gpt-5</code>, <code>gpt-5-mini</code>, <code>gpt-4o</code>, <code>gpt-4o-mini</code></td></tr><tr><td><a href="#aws-bedrock">AWS Bedrock</a></td><td>AWS Credentials</td><td><code>claude-opus-4.6</code>, <code>claude-sonnet-4.6</code>, <code>claude-opus-4.5</code>, <code>claude-sonnet-4.5</code>, <code>claude-haiku-4.5</code></td></tr><tr><td><a href="#anthropic">Anthropic</a></td><td>API Key</td><td><code>claude-opus-4.6</code>, <code>claude-sonnet-4.6</code>, <code>claude-opus-4.5</code>, <code>claude-sonnet-4.5</code>, <code>claude-haiku-4.5</code></td></tr><tr><td><a href="#azure-openai">Azure OpenAI</a></td><td>API Key + Endpoint</td><td><code>gpt-5.2</code>, <code>gpt-5</code>, <code>gpt-5-mini</code>, <code>gpt-4o</code>, <code>gpt-4o-mini</code></td></tr><tr><td><a href="#snowflake-cortex">Snowflake Cortex</a></td><td>PAT Token</td><td><code>claude-opus-4.6</code>, <code>claude-sonnet-4.6</code>, <code>claude-opus-4.5</code>, <code>claude-sonnet-4.5</code>, <code>claude-haiku-4.5</code>, <code>openai-gpt-5</code>, <code>openai-gpt-5-mini</code></td></tr><tr><td><a href="#databricks-model-serving">Databricks Model Serving</a></td><td>PAT Token</td><td><code>databricks-claude-opus-4.6</code>, <code>databricks-claude-sonnet-4.6</code>, <code>databricks-claude-opus-4.5</code>, <code>databricks-claude-sonnet-4.5</code>, <code>databricks-claude-haiku-4.5</code>, <code>databricks-gemini-3-pro</code>, <code>databricks-gemini-3-flash</code>, <code>databricks-gemini-2.5-pro</code>, <code>databricks-gemini-2.5-flash</code>, <code>databricks-gpt-5.2</code>, <code>databricks-gpt-5</code>, <code>databricks-gpt-5-mini</code></td></tr><tr><td><a href="#oracle-generative-ai">Oracle Generative AI</a></td><td>OCI Credentials</td><td><code>google.gemini-2.5-pro</code>, <code>google.gemini-2.5-flash</code>, <code>xai.grok-4</code></td></tr></tbody></table>

#### OpenAI

Connect directly to OpenAI's API.

**Supported models**: `gpt-5.2-pro`, `gpt-5.2`, `gpt-5`, `gpt-5-mini`, `gpt-4o`, `gpt-4o-mini`

**Configuration**:

* **API Key** (required): Your OpenAI API Key
* **Base URL** (optional): Custom API endpoint URL

***

#### Anthropic

Connect directly to Anthropic's API.

**Supported models**: `claude-opus-4.6`, `claude-sonnet-4.6`, `claude-opus-4.5`, `claude-sonnet-4.5`, `claude-haiku-4.5`

**Configuration:**

* **API Key** (required): Your Anthropic API Key

***

#### Google AI Studio

Connect to Google's AI Studio API.

**Supported models**: `gemini-3-pro`, `gemini-3-flash`, `gemini-2.5-pro`, `gemini-2.5-flash`

**Configuration:**

* **API Key** (required): Your Google AI Studio API Key

***

#### Google Vertex AI

Connect to Gemini and Claude models via Google Cloud Platform.

**Supported models**: `gemini-3-pro`, `gemini-3-flash`, `gemini-2.5-pro`, `gemini-2.5-flash`, `claude-opus-4.6`, `claude-sonnet-4.6`,`claude-opus-4.5`, `claude-sonnet-4.5`

**Configuration:**

* **Project ID** (required): Your GCP project ID
* **Location** (required): GCP region (e.g., us-central-1)
* **Service Account Credentials** (required): JSON credentials for a service account with Vertex AI access.

***

#### AWS Bedrock

Access Claude models through AWS infrastructure.

**Supported models**: `claude-opus-4.6`, `claude-sonnet-4.6`,`claude-opus-4.5`, `claude-sonnet-4.5`, `claude-haiku-4.5`

**Configuration:**

* **AWS Access Key ID** (required)
* **AWS Secret Access Key** (required)
* **AWS Region** (required): e.g., us-east-1

***

#### Azure OpenAI

Access OpenAI models through Azure infrastructure.

**Supported models**: `gpt-5.2`, `gpt-5`, `gpt-5-mini`, `gpt-4o`, `gpt-4o-mini`

**Configuration**:

* **API Base** (required): Your Azure OpenAI endpoint URL
* **API Key** (required): Your Azure OpenAI API key
* **API Key Version** (required): API version (e.g., 2025-01-01-preview)

***

#### Snowflake Cortex

Access AI models directly within your Snowflake environment

**Supported models**: `claude-opus-4.6`, `claude-sonnet-4.6`,`claude-opus-4.5`, `claude-sonnet-4.5`, `claude-haiku-4.5`, `openai-gpt-5`, `openai-gpt-5-mini`

**Configuration:**

* **API Base** (required): Your Snowflake Cortex endpoint (e.g., `https://myorg-myaccount.snowflakecomputing.com/api/v2/cortex/inference:complete`)
* **API Keys** (required): Personal Access Token (PAT)

***

#### Databricks Model Serving

Access models through Databricks serving endpoints.

**Supported models:** `databricks-claude-opus-4.6`, `databricks-claude-sonnet-4.6`,`databricks-claude-opus-4.5`, `databricks-claude-sonnet-4.5`, `databricks-claude-haiku-4.5`, `databricks-gemini-3-pro`, `databricks-gemini-3-flash`, `databricks-gemini-2.5-pro`, `databricks-gemini-2.5-flash`, `databricks-gpt-5.2`, `databricks-gpt-5`, `databricks-gpt-5-mini`

**Configuration**:

* **API Base** (required): Your Databricks serving endpoint URL.
* **API Key** (required): Databricks Personal Access Token

***

#### Oracle Generative AI

Access models through Oracle Cloud.

**Supported models**: `google.gemini-2.5-pro`, `google.gemini-2.5-flash`, `xai.grok-4`

**Configuration:**

* **OCI User OCID** (required)
* **OCI Tenancy OCID** (required)
* **OCI Fingerprint** (required)
* **OCI Private Key** (required)
* **OCI Region** (required): e.g., us-ashburn-1

{% hint style="info" %}
When you **configure a custom provider, it replaces the CARTO-managed models**. Only the models from your configured providers will be available when creating AI Agents.
{% endhint %}

{% hint style="info" %}
**Interested in other providers or models?** We're continuously expanding our AI provider support. If you'd like to see a specific provider or model added, pleas share your feedback with us.&#x20;
{% endhint %}

## Managing Models

From the CARTO AI settings page, you can:

* **Add providers:** Configure credentials for a supported provider to make its models available to the organization.
* **Remove providers:** Disable a provider to remove its models from availability. Any models from that provider will no longer be selectable for new agents or AI features.
* **Set default model**: Choose which model to use by default for all CARTO AI features.
* **View available models:** See the full list of models currently available to the organization across all configured providers.

## AI Features

Currently, the following AI Features are available in the CARTO platform:

* [**AI Agents**](https://docs.carto.com/carto-user-manual/ai-agents): Enable Editor users to create conversational agents that analyze and interact with maps, using available CARTO tools and MCP tools to provide insights directly in the interface.

<figure><img src="https://3029946802-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FybPdpmLltPkzGFvz7m8A%2Fuploads%2Fgit-blob-454995b435042718a5e81d04b276d0fb3cca52d4%2FScreenshot%202025-10-04%20at%2009.35.54.png?alt=media" alt=""><figcaption></figcaption></figure>