Skip to main content

​
At a glance

  • Availability: Experimental (how to enable).
  • Authentication: API key.
  • Connection: The key from OPENAI_API_KEY is sent as the Bearer prefixed Authorization header.
  • Provider documentation: Authentication reference.

​
Credentials

Set these per environment. See Connect an integration.

​
Setup

  1. Create an OpenAI account: Go to https://platform.openai.com and sign up or sign in. New accounts may need to add billing details under Settings → Billing before API calls succeed.
  2. Create an API key: Open https://platform.openai.com/api-keys, click ‘Create new secret key’, give it a descriptive name (e.g. ‘Veryfront Integration’), and select the project it belongs to.
  3. Copy and store the key: Copy the key immediately - it is only shown once. Add it to your .env file as OPENAI_API_KEY=sk-…
  4. Verify access: Run the List Models tool to confirm the key works. If you get a 401, check the key; if a 429, check your billing/quota.

​
Provider notes

  • Use project-scoped API keys to limit blast radius; you can revoke keys at any time from the dashboard
  • API usage is billed per token - set usage limits under Settings → Limits
  • The Get Completions Usage and Get Costs tools call the organization usage API, which only accepts admin API keys created at https://platform.openai.com/settings/organization/admin-keys - set one as OPENAI_API_KEY to use them
  • The Upload File tool sends multipart/form-data with a binary file part; pass the file content base64-encoded
Provider API reference.

​
Tools

​
Verify the connection

Call a read tool such as openai__list_models with arguments for your account. Confirm that the result comes from the intended account or workspace before enabling write tools.