OpenAI Connection
The OpenAI connection type enables automations to call OpenAI's API for language generation, embeddings, image generation, and transcription. It is used by any plugin or step that targets GPT-4o, GPT-4 Turbo, GPT-3.5 Turbo, DALL-E, Whisper, or the Embeddings API.
Connection Details
| Property | Value |
|---|---|
| Type ID | OPENAI |
| Category | AI Platforms |
| Testable | Yes |
Friendly Example
| What you enter | Example |
|---|---|
| Connection name | OpenAI - Ticket Summariser |
| Used for | Summarising support tickets and drafting suggested replies inside a workflow |
| Main details to collect | Secret API key, billing-verified account, optional organization/project IDs |
| Best person to provide it | AI platform owner or the engineer who manages the OpenAI account |
After it is saved, workflow builders select OpenAI - Ticket Summariser in a node instead of re-entering credentials every time.
Mandatory Fields
| Field | What It Means | Example |
|---|---|---|
apiKey | The secret key used to authenticate every request to the OpenAI API. Starts with sk-. Encrypted at rest. | sk-proj-abc123... |
The key is shown only once when you create it. Store it in a password manager or directly in Qinfinite — never paste it into code or chat.
Advanced Fields
| Field | What It Means | Example |
|---|---|---|
organizationId | Scopes usage and billing to a specific OpenAI organization. Required if your user account belongs to more than one org. | org-RaBcDeFgH |
projectId | Scopes requests to a specific project within the organization. Useful for separating cost tracking by team or use-case. | proj-XyZ789 |
defaultModel | The model to use when a workflow step does not specify one explicitly. | gpt-4o |
baseUrl | Override the API base URL. Use this for Azure OpenAI endpoints or a corporate proxy. Defaults to https://api.openai.com/v1. | https://my-company.openai.azure.com/ |
gpt-4o, gpt-4o-mini, gpt-4-turbo, gpt-3.5-turbo, text-embedding-3-small, text-embedding-3-large
Rate limits, context windows, and pricing differ by model. Check the OpenAI model overview for the latest details.
Setup Instructions
-
Sign in to platform.openai.com. Create an account if you do not have one.
-
Open the API Keys page. Click your profile avatar in the top-right corner, choose API Keys, then click Create new secret key. Give it a descriptive name such as
Qinfinite Automation. -
Copy the key immediately. OpenAI shows the full key only once. Paste it into Qinfinite's API Key field before closing the dialog.
-
Set up billing. Navigate to Settings → Billing and add a payment method. Requests fail with a
429error if there is no active payment method or if your usage limit is reached. -
(Optional) Locate your Organization ID and Project ID. Go to Settings → Organization to find the org ID (format
org-...). Project IDs appear under Settings → Projects. Add these to the Advanced Fields if you need cost isolation between teams.
Troubleshooting
| Symptom | Likely Cause | Fix |
|---|---|---|
401 Incorrect API key provided | The API key is wrong, revoked, or was copied with extra whitespace | Regenerate a fresh key on platform.openai.com and update the connection |
429 You exceeded your current quota | No active billing method, or you have hit your monthly spend limit | Add or verify a payment method under Settings → Billing; increase the spend limit if needed |
429 Rate limit reached for requests | Too many calls per minute for your tier (free / tier 1–5) | Add a retry with exponential back-off in the workflow, or request a rate limit increase |
404 The model does not exist | The defaultModel field contains a model name your account cannot access | Use a model your subscription tier supports, or request access in the OpenAI console |