Managing AI Providers
Zuplo's AI Gateway supports integration with various AI providers, allowing you to leverage different models and services for your apps.
Provider permissions
AI providers are configured for a Zuplo project. A Zuplo account contains one or more projects: an account role can grant access across those projects, while a project role grants access only to that project. Adding, editing, or deleting providers and their models requires the Edit permission granted to Zuplo account and Zuplo project Admins. A Zuplo account Developer, or a Zuplo project Developer or Member, can view providers but can't manage them. Team membership doesn't grant provider access. See Role Permissions.
Adding a New AI Provider
To add a new AI provider to your Zuplo AI Gateway, follow these steps:
-
Open Settings → AI Providers in your AI Gateway project in the Zuplo Portal.
-
Click on the Add Provider button.
-
Select the desired provider from the list of supported providers, or add a custom provider. A custom provider's API URL is its origin root—without the
/v1suffix vendors usually publish—because the gateway appends the operation path itself. -
Review the Provider Name, which fills in automatically based on the provider you selected (a second OpenAI configuration becomes
openai-2). You can replace it with your own name, but only now—the name is permanent after creation. Apps reference this provider's models asproviderName/model—for example, a provider namedopenaiservesopenai/gpt-5-mini. -
Enter the API Key for the selected provider. For instructions on how to create an API key for each provider see the provider documentation. The Zuplo Demo provider asks for no API key—your gateway authenticates to the demo service itself, Bedrock Mantle additionally asks for an AWS Region and accepts only long-term Bedrock API keys, Vertex AI asks for a Location and a Google Cloud Project ID and takes a service account JSON key file instead of an API key, and Azure AI asks for an Azure Resource Name and a host family, plus a mapping for any deployment named differently from the model it serves.
-
Select the model or models you want to use with this provider. The available models will depend on the selected provider. This can be changed later.
Click "Select All" to enable all models.
-
Click save
Saving provider settings triggers an automatic production deployment of your gateway, because provider credentials are part of the deployed gateway. The change is live once the deployment completes.
Editing an AI Provider
To modify an existing provider, open Settings → AI Providers and click the Edit button next to the provider you want to modify.
You can modify the API key and selected models for the provider—and, for
Bedrock Mantle, the AWS Region, for
Vertex AI, the Location and Google Cloud Project ID, or for
Azure AI, the Azure Resource Name, host family, and deployment
mappings. The Provider Name isn't editable: it's the routing address in
every providerName/model reference, so renaming it would orphan each stored
reference to this provider. After making your changes, click Save to apply
them.
Be careful removing models from a provider that's in use as it may break existing apps that rely on the provider. Requests for a model that's no longer available fail with an error naming the model.
Deleting an AI Provider
Providers that are no longer used within your Zuplo project can be deleted. To delete a provider, open Settings → AI Providers and click the Delete button next to the provider you want to remove.