At a glance
- Availability: Experimental (how to enable).
- Auth: API key.
- Connection: The key from
OPENAI_API_KEYis sent as theBearerprefixedAuthorizationheader. - Docs: https://platform.openai.com/docs/api-reference/authentication
Credentials
Set these per environment. See Connect an integration.| Variable | Required | Description |
|---|---|---|
OPENAI_API_KEY | Yes | OpenAI API key (starts with sk-) Docs. |
Setup
- 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.
- 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.
- 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-…
- 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.
- 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
Tools
| Tool | Access | Description |
|---|---|---|
| List Models | Read | List the models available to the API key |
| Get Model | Read | Get details about a specific model |
| Create Response | Write | Generate a model response using the OpenAI Responses API |
| Create Chat Completion | Write | Generate a chat completion from a list of messages |
| Create Embedding | Write | Create an embedding vector for input text |
| Generate Image | Write | Generate an image from a text prompt |
| Upload File | Write | Upload a file for use with assistants, batch, fine-tune, vision, user_data, or evals |
| List Files | Read | List files uploaded to the organization, optionally filtered by purpose |
| Get File | Read | Get metadata about an uploaded file by ID |
| Delete File | Write | Delete an uploaded file and remove it from all vector stores |
| Get Completions Usage | Read | Get token usage for completions across the organization, bucketed over time. Requires an organization admin API key (created under Settings → Organization → Admin keys) set as OPENAI_API_KEY - a regular project key returns 401 |
| Get Costs | Read | Get daily spend (in USD) for the organization, bucketed by day. Requires an organization admin API key (created under Settings → Organization → Admin keys) set as OPENAI_API_KEY - a regular project key returns 401 |
| Get File Content | Read | Download the raw contents of an uploaded file by ID - required to read batch output files and other generated artifacts |
| Get Embeddings Usage | Read | Get token usage for embeddings across the organization, bucketed over time. Requires an organization admin API key (created under Settings → Organization → Admin keys) set as OPENAI_API_KEY - a regular project key returns 401 |
Example prompts
- List the OpenAI models available to my API key and summarize what each is best for.
- Use OpenAI to generate a response to a prompt I provide.