Configure BYOK for dbt Wizard in dbt platform
Use bring-your-own-key (BYOK) to connect dbt Wizard or dbt Copilot in dbt platform to your own AI provider account instead of using dbt Labs' managed infrastructure.
The following BYOK instructions apply to dbt platform only. For CLI BYOK setup, refer to Configure BYOK for dbt Wizard.
When you configure a provider with your own key, usage costs appear on your provider account instead of your dbt Labs account, and token costs are billed by whichever provider you choose.
Prerequisites
- A dbt platform account on Starter, Enterprise, or Enterprise+ plans
- dbt admin permissions to enable AI features and configure providers in Account settings
- AI features enabled for your account — refer to Enable AI in dbt platform
- An API key or credentials for your supported AI provider
Configure AI provider
Once AI features have been enabled, Enterprise and Enterprise+ accounts can configure a custom AI provider. If you bring your own provider, you will incur API calls and associated charges from that provider.
* Managed (or Managed by dbt Labs): dbt Labs manages the AI provider connection; no user provider key is required. Refer to Billing for more information.
dbt Wizard
To configure your AI provider for dbt Wizard:
- Click on your account name and select Account settings in the side menu.
- Under Settings, click AI features.
- Under AI providers, click Edit to configure the AI integration.
- For each provider, select your Key management option from the dropdown.
- OpenAI
- Azure AI Foundry
- Anthropic
Managed by dbt Labs (default, no setup required). Refer to Billing for more information.*
- Select the toggle for dbt Labs to use dbt Labs' managed* OpenAI key.
- Click Save.
Managed by you (Enterprise or Enterprise+ plans)
- Select OpenAI from the options.
- Enter your OpenAI API key.
- Click Save.
OpenAI projects with data residency controls enabled and configured for the United States (project region set to US) don't currently support BYOK. These projects can only use the API key in the dbt platform configuration. Specifying custom endpoints required for data residency isn’t yet supported, and we’re evaluating a solution for this.
To use BYOK, ensure your OpenAI project doesn’t have data residency controls enabled. Projects without project region settings will use the standard OpenAI endpoint (https://api.openai.com) and support BYOK.
- For BYOK, enable the latest text generation models as well as the
text-embedding-3-smallmodel. - Ensure your project doesn't have data residency controls enabled. Projects without project region settings use the standard OpenAI endpoint (https://api.openai.com) and support BYOK.
Managed by you only (Enterprise or Enterprise+ plans)
To learn about deploying models on Azure, refer to Deploy models on Azure OpenAI and Azure AI Foundry. Configure credentials for your Azure AI Foundry deployment in dbt as follows:
- Locate your deployment details in the Azure portal (Azure AI Foundry or Azure OpenAI).
- Enter your Azure API key.
- Enter the Endpoint, API Version, and Deployment / AI model name.
- Click Save.
For the Endpoint field, enter the full Azure Target URI from Azure — not just the base endpoint. Entering only the base endpoint (for example, https://<resource>.openai.azure.com) prevents credential validation and blocks setup.
Supported formats include:
https://<resource>.openai.azure.com/openai/deployments/<deployment>/chat/completions?api-version=<version>https://<resource>.openai.azure.com/openai/responses?api-version=<version>
Managed by dbt Labs (default, no setup required). Refer to Billing for more information.*
- Select dbt Labs from the list to use dbt Labs' managed* Anthropic key.
- Click Save.
Managed by you (Enterprise or Enterprise+ plans)
- Select Anthropic from the options.
- Enter your Anthropic API key.
- Click Save.
When using an Anthropic API key, dbt continues to use the dbt Labs-managed OpenAI key for embeddings in text_to_sql MCP tools, since Anthropic doesn't natively provide embeddings.
dbt Copilot
To configure your AI provider for dbt Copilot:
- Click on your account name and select Account settings in the side menu.
- Under Settings, click Copilot.
- Under AI providers, click Edit to configure the AI integration.
- For each provider, select your Key management option from the dropdown.
- dbt Labs OpenAI
- OpenAI
- Azure OpenAI
- Select the toggle for dbt Labs to use dbt Labs' managed* OpenAI key.
- Click Save.
Bringing your own OpenAI key is available for Enterprise or Enterprise+ plans.
- Select the toggle for OpenAI to use your own OpenAI key.
- Enter the API key.
- Click Save.
OpenAI projects with data residency controls enabled and configured for the United States (project region set to US) don't currently support BYOK. These projects can only use the API key in the dbt platform configuration. Specifying custom endpoints required for data residency isn’t yet supported, and we’re evaluating a solution for this.
To use BYOK, ensure your OpenAI project doesn’t have data residency controls enabled. Projects without project region settings will use the standard OpenAI endpoint (https://api.openai.com) and support BYOK.
Bringing your own Azure OpenAI key is available for Enterprise or Enterprise+ plans.
To learn about deploying your own OpenAI model on Azure, refer to Deploy models on Azure OpenAI. Configure credentials for your Azure OpenAI deployment in dbt as follows:
- Locate your Azure OpenAI configuration in your Azure Deployment details page.
- Enter your Azure OpenAI API key.
- Enter the Endpoint, API Version, and Deployment / Model Name.
- Click Save.
For the Endpoint field, enter the full Azure Target URI from Azure — not just the base endpoint. Entering only the base endpoint (for example, https://<resource>.openai.azure.com) prevents credential validation and blocks setup.
Supported formats include:
https://<resource>.openai.azure.com/openai/deployments/<deployment>/chat/completions?api-version=<version>https://<resource>.openai.azure.com/openai/responses?api-version=<version>
- For BYOK, enable the latest text generation models as well as the
text-embedding-3-smallmodel. - Ensure your project doesn't have data residency controls enabled.
dbt Wizard is available in Studio IDE as a public preview feature, and as a standalone beta feature across the managed dbt platform. However, certain customers may have disabled experimental features, in which case, they can use Wizard CLI via terminal-access and will continue to have access to dbt Copilot until dbt Wizard is released as generally available to all customers. Contact dbt Support with any questions.
Please contact dbt Support with any questions
Was this page helpful?
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.


