Adding an AI provider in elvex is how you allow your elvex users to access LLMs that will power the agents you build in elvex. Without an AI provider, users won't have access to any large language models (LLMs), rendering the agents non-functional. Here’s how you can add one or more AI Providers to your account.
Note: Only elvex Admin users have the authority to add AI providers.
Supported AI Providers
elvex currently supports the following AI providers:
OpenAI
Azure OpenAI
Anthropic
Google Gemini
Cohere
Mistral
AWS Bedrock
Additional providers will be supported in the future
Step-by-Step Guide to Adding an AI Provider
Navigate to Settings: Click on "Settings" from the left navigation menu
Select "AI Providers": In Settings, click the "AI Providers" option
Click "Add a Provider": From AI Providers, click the "Add a Provider"
Enter Provider Details: Fill in the required fields
Provider Name: If left blank, this field will default to the name of the Provider (e.g., OpenAI, Anthropic, etc.). If this is fine, you can move to the next field, or you can add a more descriptive name.
API Key: The API key provided by the AI provider.
For example, you can find instructions on how to create an API key for:
Create a New Agent: To test the integration, create a new agent and send a test message. A simple passthrough agent to GPT-4o would suffice. [Click here to learn more about creating agents].
Send a Test Message: Use the newly created agent to send a test message to ensure that the AI provider is functioning correctly.
Important Notes on Generating an API Key from an AI Provider
Read & Write Access: elvex will need read and write access to connect with the AI Provider of your choice. If the API key you generate for the AI Provider does not have read and write access, the connection between elvex and that provider will not be successful.
Fund Your Provider Account: The account you generate the AI Provider API key from must be funded and connected with a valid credit card, otherwise the API key will generate an error when trying to use it.
Getting AWS Bedrock Credentials and Model ID
If you wish to use AWS Bedrock to host your models we recommend following the AWS Getting Started document here: https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html
For a quick step by step tutorial, follow these steps to get the Access Key ID, Secret Access Key, and Model ID you’ll need to use AWS Bedrock.
1. Create an IAM User (Programmatic Access)
Go to the AWS Management Console → IAM → Users → Create user
Enable Programmatic access (this generates access keys)
Attach a policy that allows Bedrock use:
For testing: AmazonBedrockFullAccess
For production: create a least-privilege policy with only the actions you need (`bedrock:InvokeModel`, `bedrock:ListFoundationModels`, etc.)
2. Create (or View) the Access Keys
After creating the IAM user, open the user page
Go to the Security credentials tab → Create access key
Copy and save both the Access Key ID and Secret Access Key
Store these access keys securely for later use
Note: The Secret Access Key is only shown once. If lost, you must generate a new one.
3. Enable Model Access
In the AWS Console go to Amazon Bedrock
Navigate to Model access (under Bedrock configurations)
Click Modify model access and request access for the models you need
Accept any required agreements (e.g., provider EULAs)
Wait for access to be granted (usually a few minutes)
4. Find the Model ID
Go to the Bedrock console → Base models list. Click a model to view its Model ID
5. Setup up an elvex Provider
Go to elvex Settings → AI Providers
Click Add a Provider
Choose Bedrock
Enter an optional Name, your AWS Access Key ID, AWS Secret Access Key, and Model ID
Click Add
You will now be able to choose this model as a provider in your elvex agents!
Adding Azure OpenAI
When adding Azure OpenAI, you will need to provide specific configuration details from your Azure portal in addition to the standard fields.
Select Azure OpenAI: From the Provider dropdown menu, select Azure OpenAI
Enter a name to help identify this provider. If left blank, it defaults to "OpenAI"
Enter the Endpoint URL for your resource.
This typically follows the format:
https://{resource-name}.openai.azure.com
Enter your API Key
You can find this value in the Keys & Endpoint section when examining your resource from the Azure portal
Enter the Deployment Name
This value corresponds to the custom name you chose for your deployment when you deployed a model.
You can find this value under Resource Management > Deployments in the Azure portal or alternatively under Management > Deployments in Azure OpenAI Studio.
Select a Model from the dropdown menu
Note: This model selector is for display purposes only. Each deployment has a model associated with it on the Azure side. The actual model used by the agent will be whatever model is configured in your Azure deployment settings, regardless of what is selected here.