Introduction
Use the Planck app on Zapier to generate chat completions from any supported model through the Planck AI Gateway. Provide your Planck API key, select a model, and pass your prompt data from any Zapier trigger — all with full observability in Planck.The Zapier action uses Planck’s OpenAI-compatible Chat Completions API. No OpenAI or third‑party provider keys are required when using the AI Gateway.
Integration Steps
1
Create a Planck API key
Create a Planck account at inquantum.ai and generate an
API key.
You can use a write-only key for logging requests. Learn more about
Planck-Auth.
2
Add the Planck app in Zapier
- In Zapier, create a new Zap (or edit an existing one).
- For the Action step, search for and select “Planck”.
- Choose the “Chat Completion” action.
- When prompted, connect your Planck account and paste your Planck API key.
3
Configure the Chat Completion action
- Model: pick any supported model (see model registry).
- Messages: map your trigger fields (e.g., prompt text) into the user message.
The action routes through Planck’s AI Gateway. You can later change the target provider or model in Planck without updating your Zap.
4
Test and publish your Zap
- Run a test to see the model’s response.
- Publish the Zap when you’re satisfied.
5
Verify in Planck
Open your Planck dashboard and check the Requests tab to see your Zapier‑originated requests, costs, and latencies.
Example Use Cases
- Auto‑draft replies from form submissions or support tickets
- Summarize new rows in Google Sheets or Airtable
- Generate product descriptions from e‑commerce triggers
Alternate Use cases
In case you want to utilize the observability side of Planck (rather than just the gateway), we’ve got you covered! This integration has searches and other creation actions that you could otherwise do in the Planck Dashboard It also has a blank curl request, in the event that you don’t find an action you want. Create what you need!Troubleshooting
- Ensure your Planck API key is valid and has write access.
- If a request fails, review the error in the Zap run details and the corresponding request in Planck for provider/model‑specific messages.
- To switch models later, update the model field in the Zap action or use Planck routing/policies to control traffic centrally.