Connect Google Gemini (AI Studio)

≈ 2 min Extension Web app JWT

Note — 

This page is about Gemini API keys. To read your Gmail, Drive, Sheets or Calendar, see Connect Google: that is a different kind of connection.

Before you start

• A Google account. AI Studio keys work without a Cloud project; Vertex AI keys need a Google Cloud project with billing.

Used by

• Chat Google
• Google Embeddings
• Aria and agents (Settings › Providers)

Pick a method

Method	Use it when
Aria & agents Recommended	Chat with Aria or an agent on Google Gemini models. The key is kept in Settings › Providers.
Workflow nodes	Use Chat Google, Google Embeddings in a workflow. The key is a saved credential.

Set it up

Aria & agents (recommended)

1. Create a key. In Google AI Studio, open Get API key, click Create API key and copy it. For Vertex AI, create the key in the Google Cloud Console instead.
2. Open Settings › Providers and click + Add provider.
3. Pick Google as the Provider, give it a Label and paste the key into API key.
4. Type the Model id (a gemini-… id), then click Add.
5. Optionally click Set as default, so Aria and agents set to Same as Aria use it.

Check it's connected — 

Open a chat, pick the provider’s model in the model menu and send Hello: the reply comes from Google Gemini. A wrong key shows a provider error in the chat right away.

Workflow nodes

1. Create a key. In Google AI Studio, open Get API key, click Create API key and copy it. For Vertex AI, create the key in the Google Cloud Console instead.

2. Save it in AWFlow. Open Credentials and click Add Credential (or + Add Credential in the node’s Authentication field), then fill the New Credential form. In the browser side panel the form comes in two steps: tap Simple Credential (or click Continue), then fill the rest.

   123456

   1. 1 Step 1:Keep it a simple credential Leave Integration App / Service on Select an integration..., or pick Simple Credential at the top of its list.
   2. 2 Step 2:Name it For example Google Gemini – personal. A Description is optional.
   3. 3 Step 3:Set Auth Type to JWT Open Auth Type and choose JWT.
   4. 4 Step 4:Paste the key Paste the key into JWT, exactly as copied.
   5. 5 Step 5:Check where it is saved Signed in, choose Local (this browser only) or Cloud (synced to your account) under Storage location. Without an account it is saved locally in this browser, as here.
   6. 6 Step 6:Click Create Credential Check: the credential is listed on the Credentials page, ready to pick in nodes.

   Numbered areas in the screenshot: 1. Integration App / Service: none (Simple Credential); 2. Name; 3. Auth Type: JWT; 4. JWT; 5. Where the secret is stored (here, locally in this browser); 6. Create Credential.

3. Pick it in the node. In Chat Google, choose the credential in Authentication and type the Model id.

Check it's connected — 

Connect Chat Google to an AI node (for example a Basic LLM Chain with the prompt Say hello) and click Test step on the AI node: you get a reply.

Where your token lives

Where your token lives — 

The credential is stored where you choose when you create it:

• Local (this browser only): encrypted in this browser. The encryption key is kept on the same device, so turn on the local secret vault to lock it with a passphrase only you know.
• Cloud (synced to your account): sent over an encrypted connection and stored encrypted on AWFlow’s server, so it works on your other devices.

When a step runs, your browser sends it only to generativelanguage.googleapis.com (AI Studio) and aiplatform.googleapis.com (Vertex AI). AWFlow’s servers never relay the call.

Keys added in Settings › Providers are separate: they stay on this device only, encrypted, and are never synced to your account.

Privacy & your data →

Common issues

• A 401, “invalid API key” or “Incorrect API key” error. The key was mistyped, revoked, or belongs to another account. Create a new key and update the credential (or the provider in Settings › Providers).
• A 429 or “quota” error. The account is out of credit or over its rate limit. Add credit or wait, then run again.
• An embeddings node fails with 401 while a chat node with the same key works. The credential is a Bearer Token. Embeddings nodes pass the value to the provider as it is, so use a JWT credential that holds only the key.
• “API key not valid” with a Vertex AI key. In Chat Google, set Platform Type to gcp. Leave it empty or on gai for an AI Studio key.

Related

Chat Google node

All connections

Create and manage credentials

Privacy & your data