LLM Configuration

ekai uses Large Language Models (LLMs) for AI-powered features including schema onboarding, ERD generation, BRD interviews, and artifact generation. Configure your LLM provider based on your organization's security and compliance requirements.

Owner Access Only

LLM Configuration is only accessible to account Owners. Admins and Users do not see this menu item.

Configuration Screen

Navigate to LLM Configuration in the sidebar to configure your AI provider.

Provider Types

Public LLM APIs

Connect to hosted models via standard API keys.

Provider	Models
Anthropic	Anthropic Claude Opus 5, Anthropic Claude Sonnet 5, Anthropic Claude Haiku 4.5
OpenAI	OpenAI GPT 5.6 Sol, OpenAI GPT 5.6 Terra, OpenAI GPT 5.6 Luna, OpenAI text-embedding-3-large
Google Gemini	Gemini 3.7 Flash, Gemini gemini-embedding-2

Use case: Quick setup, standard security requirements

Note: When using Anthropic models, you will also need to add Google Gemini key to avail gemini-embedding-2 for document indexing.

Snowflake Cortex LLMs

Run models directly within Snowflake. Complete in-platform processing.

Provider	Models
Snowflake Cortex	Claude Opus 5, Claude Sonnet 5, Claude Haiku 4.5, Cortex arctic-embed-l-v2.0

Use case: Enhanced security, Snowflake Native App deployments

Enterprise Cloud APIs

Use secure, private endpoints via your enterprise cloud accounts.

Provider	Models
Google Vertex AI	Vertex Claude Opus 5, Vertex Claude Sonnet 5, Vertex Claude Haiku 4.5, Vertex gemini-embedding-001
Azure OpenAI	Azure OpenAI GPT 5.6 Sol, Azure OpenAI GPT 5.6 Terra, Azure OpenAI GPT 5.6 Luna, Azure OpenAI text-embedding-3-large
AWS Bedrock	Claude via AWS

Use case: Enterprise security, data residency, compliance

Model Availability

Ensure required models are enabled in your cloud environment:

Google Vertex AI: Enable Vertex AI APIs and models
Azure OpenAI: Request model access and deployments
AWS Bedrock: Enable model access in Bedrock

Configuration Steps

Public APIs

Navigate to LLM Configuration in the sidebar
Select Public APIs
Enter API keys for your chosen providers:
- Anthropic API key
- OpenAI API key
- Google AI API key
Click Test to verify connectivity
Click Save

Enterprise Cloud (Google Vertex AI)

Select Enterprise Cloud
Choose Google Cloud Platform tab
Upload your Service Account JSON key or paste the content
Click Test to verify connectivity
Click Save

Service Account Requirements:

Vertex AI User role
Access to Claude and/or Gemini models
Appropriate project permissions

Enterprise Cloud (Azure OpenAI)

Select Enterprise Cloud
Choose Azure tab
Enter Azure OpenAI credentials:
- Endpoint URL
- API Key
- Deployment names
Click Test and Save

Enterprise Cloud (AWS Bedrock)

Select Enterprise Cloud
Choose AWS tab
Enter AWS credentials:
- AWS Access Key ID
- AWS Secret Access Key
- AWS Region
Click Test and Save

IAM Requirements:

bedrock:InvokeModel permission
Access to Claude models

Try It Out

Hands on overview of how to configure LLMs

Test the LLM configuration interface with this interactive demo. Use the credentials below to simulate a successful connection:

Demo Credentials

Paste the following dummy credentials in relevant fields to try out model configuration.

Public APIs:

Anthropic: sk-ant-demo-2026
OpenAI: sk-proj-demo-2026
Gemini: AIza-demo-2026

Enterprise Cloud:

GCP: {"type":"service_account","project_id":"demo"}
Azure: https://demo.openai.azure.com
AWS: us-east-1

Snowflake Cortex:

PAT: demo-pat-2026