CARTO AI

CARTO AI adds AI capabilities across the CARTO platform. This includes 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.

By enabling CARTO AI, you agree to the CARTO AI terms and conditions.

Model Options

CARTO managed models (default)

When CARTO AI is enabled, it uses CARTO-managed models by default:

• gemini-2.5-pro: Recommended for geospatial use cases across CARTO AI, such as spatial reasoning, SQL generation, and high-accuracy insights.

• gemini-2.5-flash: Faster and more cost-effective, ideal for simpler queries, exploratory prompts, 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.

Supported Providers

Provider	Authentication	Use Case
Google Vertex AI	Service Account	Enterprise GCP deployments
Google AI Studio	API Key	Direct access to Gemini models
OpenAI	API Key	Direct access to GPT models
AWS Bedrock	AWS Credentials	Claude models via AWS
Snowflake Cortex	PAT Token	AI within Snowflake environment
Databricks Model Serving	PAT Token	Models via Databricks endpoints
Oracle Generative AI	OCI Credentials	Grok via Oracle Cloud
Anthropic	API Key	Direct access to Claude models
Azure OpenAI	API Key + Endpoint	GPT models via Azure

OpenAI

Connect directly to OpenAI's API.

Supported models: 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-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-2.5-pro, gemini-2.5-flash

Configuration:

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

---

Google Vertex AI

Connect to Gemini models via Google Cloud Platform.

Supported models: gemini-2.5-pro, gemini-2.5-flash

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-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, 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-sonnet-4.5, claude-haiku-4.5, openai-gpt-5, openai-gpt-5-mini, openai-gpt-4o, openai-gpt-4o-mini

Configuration:

• API Base (required): Your Snowflake Cortex endpoint.

• API Keys (required): Personal Access Token (PAT)

---

Databricks Model Serving

Access models through Databricks serving endpoints.

Supported models: databricks-gemini-2.5-pro, databricks-gemini-2.5-flash, databricks-claude-sonnet-4.5

Configuration:

• API Base (required): Your Databricks serving endpoint URL.

• API Key (required): Databricks Personal Access Token

---

Oracle Generative AI

Access models through Oracle .

Supported models: 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

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.

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.

Managing Models

From CARTO AI settings page, you can:

• Add providers: Click on a provider card to configure credentials and enable it.

• Remove providers: Disable a provider to remove its model from availability.

• View available models: See all models currently available to your organization.

AI Features

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

• 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.