Mattering Automations OpenAI integration

Connect OpenAI to Mattering Automations: chat completions, embeddings, image generation with platform file storage, and content moderation as workflow steps.

Get the credential Connect Verify Node reference Troubleshooting

The Mattering Automations OpenAI integration adds four nodes to your canvas: chat completions with GPT models, text embeddings, image generation, and content moderation.

Setup is one OpenAI API key. Image generation can optionally save its output straight into Mattering's managed file system, so downstream steps get a stable file reference instead of raw base64.

Before you start

An OpenAI account with API access and billing set up at platform.openai.com.
A Mattering workspace with access to the Automations app.

Create an OpenAI API key

The connector authenticates with an OpenAI API key sent as a bearer credential.

In the OpenAI platform, open API keys and click Create new secret key.

The secret key is shown once. Copy it now; OpenAI does not display it again.

Copy the key (it starts with sk-).

Connect OpenAI to Mattering

In Mattering Automations, open Connectors and click Add Connector.

Choose OpenAI from the list.

Click Create new credential, paste the API key, and save. The credential is stored encrypted in Google Secret Manager.

Click Test Connection: Mattering verifies the key against OpenAI's models endpoint.

Click Connect. All four OpenAI nodes appear in your canvas palette.

Verify it works

Open an automation canvas and drop OpenAI Chat onto it. Set a model and a short messages array, then run a test step: a successful response returns the completion and token usage.

To confirm image storage, run OpenAI Image with a prompt and store to platform enabled: the node output carries a managed file reference and the image appears in your platform files.

Node reference

4 nodes, generated from the connector itself so this reference always matches what ships.

Action nodes 4

OpenAI Chat

action_openai_chat_completion

Generate a chat completion with GPT models

OpenAI Embedding

action_openai_embedding

Generate text embeddings

OpenAI Image

action_openai_image_generation

Generate images with OpenAI image models

OpenAI Moderation

action_openai_moderation

Check text for content policy violations

Using the integration

On the automation canvas

Use Chat for generation and extraction, Embedding to vectorize text for search or matching, and Moderation to screen inbound content before it reaches a public surface. Every input accepts template references from prior steps.

Images that file themselves

OpenAI Image can store its output in Mattering's managed file system and return the file id, keeping workflow payloads small and making generated images browsable with the prompt kept as provenance.

From AI assistants over MCP

All four nodes speak MCP, the open protocol for connecting AI assistants to tools. Claude, ChatGPT, and Matter can run them, so you can mix model providers inside one canvas.

Troubleshooting

The image node returns a 400 saying the model does not exist

The model id is not one your account can call. Leave the model field on the node default, or set it to a current OpenAI image model id you have access to.

Test Connection fails with a 401

The API key is wrong, revoked, or truncated. Recreate it at platform.openai.com and update the credential.

Calls fail with a quota or rate limit error

OpenAI enforces per-organization rate and usage limits by model and tier. Check your usage and limits in the OpenAI dashboard; the node surfaces the API error so a workflow can retry.

The OpenAI MCP

What connecting OpenAI unlocks for AI agents and automations, with common uses and FAQs.

More guides

All Automations documentation

Every integration guide, plus how connectors, credentials, and workflows fit together.

OpenAI is a trademark of its respective owner. Mattering uses platform names to identify the services these integrations connect to; no endorsement or affiliation is implied.