How to Connect OpenAI to DAVE

Summary

The steps

1. 1

   Get your OpenAI API key

   Before you configure anything in DAVE, you need an active OpenAI API key. Log in to your OpenAI account at platform.openai.com, navigate to the API Keys section, and create a new secret key. Copy it immediately: OpenAI shows the full key value only once at creation time.

   Keep this key secure. You will paste it into DAVE's Providers screen in the next step, and once stored it will be masked in the UI and encrypted at rest with per-tenant keys. It will never be returned in plain text through the API.

   Do this

   • Log in to platform.openai.com.
   • Navigate to API Keys and create a new secret key.
   • Copy the key value and store it temporarily in a secure location such as a password manager.
   • Note which OpenAI models your account or organisation has access to. You will select from these when building the model catalog in DAVE.
   • Optionally, set a usage limit on your OpenAI account to cap spend during development and testing.

   Example

   A typical OpenAI secret key begins with sk-. If you are using a project-scoped key, it may begin with sk-proj-. Either format works in DAVE. If your key does not start with sk-, double-check you are copying from the correct account and key type.

   Best practice

   • Create a dedicated API key for DAVE rather than reusing a key shared with other tools or team members. This makes it straightforward to rotate or revoke DAVE's access independently.
   • Set a monthly spend limit on your OpenAI account to prevent unexpected charges during workflow development.
   • Never paste your API key into a workflow prompt, a node label, or any visible text field. Use the DAVE credential vault exclusively.
2. 2

   Navigate to Admin > API Management > Providers

   In your DAVE workspace, navigate to Admin → API Management → Providers. This screen lists every AI provider configured for your tenant and is where you create, edit, and delete provider records.

   Access to this screen is restricted to the Admin role. If you do not see the Providers option in the menu, you do not have Admin access for this tenant. Ask your workspace Admin to grant you the appropriate role. DAVE has six default tenant roles (Admin, Create, Curate, Use, Reporting, and Financial), and only Admin can view or manage providers.

   The Providers page displays a card for each configured provider, showing its name, provider type badge, model count, and base URI. If this is a new workspace, the list will be empty.

   Do this

   • Sign in to your DAVE workspace.
   • Open the Admin section from the main navigation.
   • Select API Management, then Providers.
   • Review any existing providers. You can have multiple providers active simultaneously and route different workflow nodes to different providers.
   • Click Add Provider in the top-right corner to open the create form.

   Example

   If your workspace already has an Anthropic or Google AI provider configured, you will see those cards listed here. Adding OpenAI creates a separate provider entry alongside them. Each provider is independent: editing or deleting one does not affect the others.

   Best practice

   • Use a descriptive name that reflects the provider's purpose and environment, for example OpenAI Production or OpenAI Staging. This name appears in agent configuration dropdowns, so clarity here saves confusion later.
   • Providers are scoped per tenant. If you manage multiple tenants in DAVE, you will need to add an OpenAI provider separately in each tenant where you want to use it.
3. 3

   Create the OpenAI provider record

   With the create form open, fill in the required fields to register OpenAI as a provider in your tenant.

   Select OpenAI from the Provider Type dropdown. Selecting this type automatically pre-fills the Base URI field with OpenAI's default API endpoint: https://api.openai.com/v1. You do not need to change this value unless you are routing through a custom proxy or a compatible endpoint, in which case you would use the OpenAI-Compatible provider type instead.

   Paste your OpenAI API key into the API Key field. The field is masked by default. Click the eye icon to toggle visibility if you need to verify the value before saving. The key is stored encrypted at rest with per-tenant keys and is never returned in plain text through the API once saved.

   Do this

   • In the Name field, enter a descriptive label such as OpenAI Production.
   • Set Provider Type to OpenAI. The Base URI auto-fills to https://api.openai.com/v1.
   • Paste your OpenAI API key into the API Key field.
   • Proceed to configure the model catalog before clicking Create Provider (see Step 4).

   Example

   A completed OpenAI provider form will show: Name = OpenAI Production, Provider Type = OpenAI, Base URI = https://api.openai.com/v1, and a masked API key. The model catalog section below the key field will be empty until you fetch or enter models.

   Best practice

   • Do not change the pre-filled Base URI unless you have a specific reason to. The default https://api.openai.com/v1 is correct for standard OpenAI accounts.
   • If you need to connect to an Azure OpenAI deployment or an OpenAI-compatible third-party endpoint, use the Azure OpenAI or OpenAI-Compatible provider type instead of the OpenAI type. Each has its own setup path.
4. 4

   Build the model catalog

   Before saving, configure the model catalog: the list of OpenAI models that will be available to agents in your workflows. DAVE offers two ways to populate this catalog.

   Fetch from API (recommended): Click the Fetch Models button. DAVE calls the OpenAI models endpoint using the API key you just entered and returns the list of models your account can access. Use the search box to filter by name, then check the models you want to include. Use the All or None buttons to bulk-select. A successful fetch also confirms that your API key and base URI are valid before you save the provider.

   JSON mode: If you prefer to specify models manually, click the JSON button and paste a JSON array of model objects. This is useful if you want to restrict the catalog to a specific subset of models regardless of what the API returns.

   Once your catalog is configured, click Create Provider to save the record.

   Do this

   • In the model catalog section, click Fetch Models.
   • Wait for DAVE to retrieve the model list from https://api.openai.com/v1.
   • Use the search box to filter models if needed (for example, search gpt-4o to find GPT-4o variants).
   • Check the models you want to include in the catalog. Uncheck any you do not need.
   • Click Create Provider to save.
   • Confirm the new provider card appears in the Providers list with the correct model count.

   Example

   After fetching, you might see models such as gpt-4o, gpt-4o-mini, and o3 in the list. Select only the models your team will actively use. A focused catalog makes model selection faster when configuring agents and reduces the chance of accidentally targeting an unintended model in a workflow.

   Best practice

   • Always use Fetch from API rather than manually entering model IDs in JSON mode. Fetching avoids typos in model identifiers and ensures you see the latest models available to your account.
   • Keep the catalog lean. Include only the models your workflows actually need. You can always edit the provider later to add more.
   • After saving, click the chevron on the provider card to expand it and verify the model list looks correct before wiring up agents.
5. 5

   Use OpenAI in a workflow node

   With the OpenAI provider saved and its model catalog populated, it is immediately available to any workflow node that calls an AI model. In DAVE's workflow runtime, nodes that invoke AI models, such as an Agent Interaction node, let you select a provider and a specific model from that provider's catalog.

   Agents are the bridge between workflow nodes and providers. When you configure an agent, you select the OpenAI provider you just created and choose a model from its catalog. The agent uses the provider's stored API key and base URI at runtime. Your workflow node then references that agent. When the node executes, DAVE calls OpenAI directly using your key. No request is proxied through DAVE's infrastructure for billing purposes: the call goes from DAVE to OpenAI, and the usage appears on your OpenAI invoice.

   Every provider call made during workflow execution is recorded in DAVE's full audit log, giving you a complete trace of which provider was called, by which agent, in which workflow, and when.

   Do this

   • Navigate to the Agents section of your workspace and create or edit an agent.
   • In the agent configuration, select your new OpenAI provider from the provider dropdown.
   • Choose the model appropriate for the agent's task (for example, gpt-4o for a reasoning-heavy step).
   • Save the agent.
   • Open or create a workflow and add an Agent Interaction node that references this agent.
   • Run a test execution to confirm the node calls OpenAI successfully and returns the expected output.
   • Check the audit log to verify the call was recorded correctly.

   Example

   A common pattern is to configure one agent targeting gpt-4o for complex reasoning steps and a second agent targeting gpt-4o-mini for faster, lower-cost summarisation steps. Both agents reference the same OpenAI provider record, so rotating the API key in one place updates both agents simultaneously.

   Best practice

   • Start with a simple single-node test workflow before wiring OpenAI into a complex multi-step pipeline. Confirm the connection, response format, and latency before building on top of it.
   • If an agent fails with an authentication or invalid API key error, navigate to Admin → API Management → Providers, edit the OpenAI provider, enter a fresh API key, and click Fetch Models to verify the new key works before saving.
   • If you are building workflows for multiple clients or regulated industries, review DAVE's SOC 2 and GDPR compliance modes, which govern how execution data, including AI provider responses, is handled and retained across your tenant.

What this guide covers

Before you start

What to check once it is connected

FAQ