google · haranrk · Jun 2, 2026 · Jun 2, 2026 · Jun 2, 2026 · Jun 2, 2026
diff --git a/.github/workflows/update-python-docs.yaml b/.github/workflows/update-python-docs.yaml
@@ -58,7 +58,7 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.ADK_BOT_GITHUB_TOKEN }}
           GOOGLE_CLOUD_PROJECT: ${{ secrets.GOOGLE_CLOUD_PROJECT }}
           GOOGLE_CLOUD_LOCATION: ${{ secrets.GOOGLE_CLOUD_LOCATION }}
-          GOOGLE_GENAI_USE_VERTEXAI: 1
+          GOOGLE_GENAI_USE_ENTERPRISE: 1
           DOC_OWNER: 'google'
           DOC_REPO: 'adk-docs'
           CODE_OWNER: 'google'

diff --git a/docs/agents/config.md b/docs/agents/config.md
@@ -88,15 +88,15 @@ To create an ADK project for use with Agent Config:
     1.  For Gemini model access through Google API, add a line to the
         file with your API key:
 
-            GOOGLE_GENAI_USE_VERTEXAI=0
+            GOOGLE_GENAI_USE_ENTERPRISE=0
             GOOGLE_API_KEY=<your-Google-Gemini-API-key>
 
         You can get an API key from the Google AI Studio
         [API Keys](https://aistudio.google.com/app/apikey) page.
 
     1.  For Gemini model access through Google Cloud, add these lines to the file:
 
-            GOOGLE_GENAI_USE_VERTEXAI=1
+            GOOGLE_GENAI_USE_ENTERPRISE=1
             GOOGLE_CLOUD_PROJECT=<your_gcp_project>
             GOOGLE_CLOUD_LOCATION=us-central1
 

diff --git a/docs/agents/models/agent-platform.md b/docs/agents/models/agent-platform.md
@@ -29,7 +29,7 @@ Ensure your environment is configured for Agent Platform:
    targets Agent Platform:
 
     ```shell
-    export GOOGLE_GENAI_USE_VERTEXAI=TRUE
+    export GOOGLE_GENAI_USE_ENTERPRISE=TRUE
     ```
 
 ## Model Garden Deployments
@@ -165,7 +165,7 @@ Agent Platform.
     **Setup:**
 
     1. **Agent Platform Environment:** Ensure the consolidated Agent Platform setup (ADC, Env
-       Vars, `GOOGLE_GENAI_USE_VERTEXAI=TRUE`) is complete.
+       Vars, `GOOGLE_GENAI_USE_ENTERPRISE=TRUE`) is complete.
 
     2. **Install Provider Library:** Install the necessary client library configured
        for Agent Platform.
@@ -296,7 +296,7 @@ Agent Platform offers a curated selection of open-source models, such as Meta Ll
     **Setup:**
 
     1. **Agent Platform Environment:** Ensure the consolidated Agent Platform setup (ADC, Env
-       Vars, `GOOGLE_GENAI_USE_VERTEXAI=TRUE`) is complete.
+       Vars, `GOOGLE_GENAI_USE_ENTERPRISE=TRUE`) is complete.
 
     2. **Install LiteLLM:**
             ```shell

diff --git a/docs/agents/models/google-gemini.md b/docs/agents/models/google-gemini.md
@@ -133,7 +133,7 @@ This is the simplest method and is recommended for getting started quickly.
 
         ```shell
         export GOOGLE_API_KEY="YOUR_GOOGLE_API_KEY"
-        export GOOGLE_GENAI_USE_VERTEXAI=FALSE
+        export GOOGLE_GENAI_USE_ENTERPRISE=FALSE
         ```
 
         (or)
@@ -165,7 +165,7 @@ For scalable and production-oriented use cases, Agent Platform is the recommende
     Explicitly tell the library to use Agent Platform:
 
     ```shell
-    export GOOGLE_GENAI_USE_VERTEXAI=TRUE
+    export GOOGLE_GENAI_USE_ENTERPRISE=TRUE
     ```
 
 4. **Models:** Find available model IDs in the
@@ -178,7 +178,7 @@ For scalable and production-oriented use cases, Agent Platform is the recommende
 2.  **Set environment variables:**
     ```shell
     export GOOGLE_GENAI_API_KEY="PASTE_YOUR_EXPRESS_MODE_API_KEY_HERE"
-    export GOOGLE_GENAI_USE_VERTEXAI=TRUE
+    export GOOGLE_GENAI_USE_ENTERPRISE=TRUE
     ```
 
 ### **Method C: Service Account (for Production & Automation)**

diff --git a/docs/deploy/cloud-run.md b/docs/deploy/cloud-run.md
@@ -56,7 +56,7 @@ Set your environment variables as described in the [Setup and Installation](../g
 ```bash
 export GOOGLE_CLOUD_PROJECT=your-project-id
 export GOOGLE_CLOUD_LOCATION=us-central1 # Or your preferred location
-export GOOGLE_GENAI_USE_VERTEXAI=True
+export GOOGLE_GENAI_USE_ENTERPRISE=True
 ```
 
 _(Replace `your-project-id` with your actual GCP project ID)_
@@ -66,7 +66,7 @@ Alternatively you can also use an API key from AI Studio
 ```bash
 export GOOGLE_CLOUD_PROJECT=your-project-id
 export GOOGLE_CLOUD_LOCATION=us-central1 # Or your preferred location
-export GOOGLE_GENAI_USE_VERTEXAI=FALSE
+export GOOGLE_GENAI_USE_ENTERPRISE=FALSE
 export GOOGLE_API_KEY=your-api-key
 ```
 *(Replace `your-project-id` with your actual GCP project ID and `your-api-key` with your actual API key from AI Studio)*
@@ -336,7 +336,7 @@ unless you specify it as deployment setting, such as the `--with_ui` option for
     --region $GOOGLE_CLOUD_LOCATION \
     --project $GOOGLE_CLOUD_PROJECT \
     --allow-unauthenticated \
-    --set-env-vars="GOOGLE_CLOUD_PROJECT=$GOOGLE_CLOUD_PROJECT,GOOGLE_CLOUD_LOCATION=$GOOGLE_CLOUD_LOCATION,GOOGLE_GENAI_USE_VERTEXAI=$GOOGLE_GENAI_USE_VERTEXAI"
+    --set-env-vars="GOOGLE_CLOUD_PROJECT=$GOOGLE_CLOUD_PROJECT,GOOGLE_CLOUD_LOCATION=$GOOGLE_CLOUD_LOCATION,GOOGLE_GENAI_USE_ENTERPRISE=$GOOGLE_GENAI_USE_ENTERPRISE"
     # Add any other necessary environment variables your agent might need
     ```
 
@@ -579,7 +579,7 @@ unless you specify it as deployment setting, such as the `--with_ui` option for
     --region $GOOGLE_CLOUD_LOCATION \
     --project $GOOGLE_CLOUD_PROJECT \
     --allow-unauthenticated \
-    --set-env-vars="GOOGLE_CLOUD_PROJECT=$GOOGLE_CLOUD_PROJECT,GOOGLE_CLOUD_LOCATION=$GOOGLE_CLOUD_LOCATION,GOOGLE_GENAI_USE_VERTEXAI=$GOOGLE_GENAI_USE_VERTEXAI"
+    --set-env-vars="GOOGLE_CLOUD_PROJECT=$GOOGLE_CLOUD_PROJECT,GOOGLE_CLOUD_LOCATION=$GOOGLE_CLOUD_LOCATION,GOOGLE_GENAI_USE_ENTERPRISE=$GOOGLE_GENAI_USE_ENTERPRISE"
     # Add any other necessary environment variables your agent might need
     ```
 

diff --git a/docs/deploy/gke.md b/docs/deploy/gke.md
@@ -8,7 +8,7 @@
 
 To deploy your agent you will need to have a Kubernetes cluster running on GKE. You can create a cluster using the Google Cloud Console or the `gcloud` command line tool.
 
-In this example we will deploy a simple agent to GKE. The agent will be a FastAPI application that uses `Gemini 2.0 Flash` as the LLM. We can use Agent Platform or AI Studio as the LLM provider using the Environment variable `GOOGLE_GENAI_USE_VERTEXAI`.
+In this example we will deploy a simple agent to GKE. The agent will be a FastAPI application that uses `Gemini 2.0 Flash` as the LLM. We can use Agent Platform or AI Studio as the LLM provider using the Environment variable `GOOGLE_GENAI_USE_ENTERPRISE`.
 
 ## Environment variables
 
@@ -17,7 +17,7 @@ Set your environment variables as described in the [Setup and Installation](../g
 ```bash
 export GOOGLE_CLOUD_PROJECT=your-project-id # Your GCP project ID
 export GOOGLE_CLOUD_LOCATION=us-central1 # Or your preferred location
-export GOOGLE_GENAI_USE_VERTEXAI=true # Set to true if using Agent Platform
+export GOOGLE_GENAI_USE_ENTERPRISE=true # Set to true if using Agent Platform
 export GOOGLE_CLOUD_PROJECT_NUMBER=$(gcloud projects describe --format json $GOOGLE_CLOUD_PROJECT | jq -r ".projectNumber")
 ```
 
@@ -319,9 +319,9 @@ spec:
             value: $GOOGLE_CLOUD_PROJECT
           - name: GOOGLE_CLOUD_LOCATION
             value: $GOOGLE_CLOUD_LOCATION
-          - name: GOOGLE_GENAI_USE_VERTEXAI
-            value: "$GOOGLE_GENAI_USE_VERTEXAI"
-          # If using AI Studio, set GOOGLE_GENAI_USE_VERTEXAI to false and set the following:
+          - name: GOOGLE_GENAI_USE_ENTERPRISE
+            value: "$GOOGLE_GENAI_USE_ENTERPRISE"
+          # If using AI Studio, set GOOGLE_GENAI_USE_ENTERPRISE to false and set the following:
           # - name: GOOGLE_API_KEY
           #   value: $GOOGLE_API_KEY
           # Add any other necessary environment variables your agent might need

diff --git a/docs/get-started/streaming/quickstart-streaming-java.md b/docs/get-started/streaming/quickstart-streaming-java.md
@@ -109,7 +109,7 @@ To run the server, you’ll need to export two environment variables:
 * a variable to specify we’re not using Agent Platform this time.
 
 ```shell
-export GOOGLE_GENAI_USE_VERTEXAI=FALSE
+export GOOGLE_GENAI_USE_ENTERPRISE=FALSE
 export GOOGLE_API_KEY=YOUR_API_KEY
 ```
 

diff --git a/docs/get-started/streaming/quickstart-streaming.md b/docs/get-started/streaming/quickstart-streaming.md
@@ -90,7 +90,7 @@ To run the agent, choose a platform from either Google AI Studio or Google Cloud
     2. Open the **`.env`** file located inside (`app/`) and copy-paste the following code.
 
         ```env title=".env"
-        GOOGLE_GENAI_USE_VERTEXAI=FALSE
+        GOOGLE_GENAI_USE_ENTERPRISE=FALSE
         GOOGLE_API_KEY=PASTE_YOUR_ACTUAL_API_KEY_HERE
         ```
 
@@ -111,7 +111,7 @@ To run the agent, choose a platform from either Google AI Studio or Google Cloud
        the following code and update the project ID and location.
 
         ```env title=".env"
-        GOOGLE_GENAI_USE_VERTEXAI=TRUE
+        GOOGLE_GENAI_USE_ENTERPRISE=TRUE
         GOOGLE_CLOUD_PROJECT=PASTE_YOUR_ACTUAL_PROJECT_ID
         GOOGLE_CLOUD_LOCATION=us-central1
         ```

diff --git a/docs/grounding/grounding_with_search.md b/docs/grounding/grounding_with_search.md
@@ -22,7 +22,7 @@ Before creating a grounded agent, you must have an existing Agent Search Data St
 * For Java, ensure your application environment has Google Cloud default credentials configured (`GOOGLE_APPLICATION_CREDENTIALS`).
 
 ```env title=".env"
-GOOGLE_GENAI_USE_VERTEXAI=TRUE
+GOOGLE_GENAI_USE_ENTERPRISE=TRUE
 GOOGLE_CLOUD_PROJECT=YOUR_PROJECT_ID
 GOOGLE_CLOUD_LOCATION=LOCATION
 ```

diff --git a/docs/integrations/bigquery-agent-analytics.md b/docs/integrations/bigquery-agent-analytics.md
@@ -103,7 +103,7 @@ shows the BigQuery view optionally created when
 
     os.environ['GOOGLE_CLOUD_PROJECT'] = 'your-gcp-project-id'
     os.environ['GOOGLE_CLOUD_LOCATION'] = 'us-central1'
-    os.environ['GOOGLE_GENAI_USE_VERTEXAI'] = 'True'
+    os.environ['GOOGLE_GENAI_USE_ENTERPRISE'] = 'True'
 
     plugin = BigQueryAgentAnalyticsPlugin(
         project_id="your-gcp-project-id",
@@ -222,7 +222,7 @@ LIMIT 20;
         # --- CRITICAL: Set environment variables BEFORE Gemini instantiation ---
         os.environ['GOOGLE_CLOUD_PROJECT'] = PROJECT_ID
         os.environ['GOOGLE_CLOUD_LOCATION'] = VERTEX_LOCATION
-        os.environ['GOOGLE_GENAI_USE_VERTEXAI'] = 'True'
+        os.environ['GOOGLE_GENAI_USE_ENTERPRISE'] = 'True'
 
         # --- Initialize the Plugin with Config ---
         bq_config = BigQueryLoggerConfig(
@@ -1437,7 +1437,7 @@ DATASET_ID = os.environ.get("BQ_DATASET", "agent_analytics")
 # region used by GOOGLE_CLOUD_LOCATION.
 BQ_LOCATION = os.environ.get("BQ_LOCATION", "US")
 
-os.environ["GOOGLE_GENAI_USE_VERTEXAI"] = "True"
+os.environ["GOOGLE_GENAI_USE_ENTERPRISE"] = "True"
 
 # --- Plugin ---
 bq_analytics_plugin = BigQueryAgentAnalyticsPlugin(

diff --git a/docs/integrations/cloud-trace.md b/docs/integrations/cloud-trace.md
@@ -44,7 +44,7 @@ working_dir/
 
     os.environ.setdefault("GOOGLE_CLOUD_PROJECT", "{your-project-id}")
     os.environ.setdefault("GOOGLE_CLOUD_LOCATION", "global")
-    os.environ.setdefault("GOOGLE_GENAI_USE_VERTEXAI", "True")
+    os.environ.setdefault("GOOGLE_GENAI_USE_ENTERPRISE", "True")
 
 
     # Define a tool function

diff --git a/docs/integrations/express-mode.md b/docs/integrations/express-mode.md
@@ -47,7 +47,7 @@ With this approach, `Session` objects are handled as children of the
 variables are set correctly, as shown below:
 
 ```env title="agent/.env"
-GOOGLE_GENAI_USE_VERTEXAI=TRUE
+GOOGLE_GENAI_USE_ENTERPRISE=TRUE
 GOOGLE_API_KEY=PASTE_YOUR_ACTUAL_EXPRESS_MODE_API_KEY_HERE
 ```
 
@@ -90,7 +90,7 @@ the session object without any project or location.
 ```py
 # Requires: pip install google-adk[vertexai]
 # Plus environment variable setup:
-# GOOGLE_GENAI_USE_VERTEXAI=TRUE
+# GOOGLE_GENAI_USE_ENTERPRISE=TRUE
 # GOOGLE_API_KEY=PASTE_YOUR_ACTUAL_EXPRESS_MODE_API_KEY_HERE
 from google.adk.sessions import VertexAiSessionService
 
@@ -119,7 +119,7 @@ the memory object without any project or location.
 ```py
 # Requires: pip install google-adk[vertexai]
 # Plus environment variable setup:
-# GOOGLE_GENAI_USE_VERTEXAI=TRUE
+# GOOGLE_GENAI_USE_ENTERPRISE=TRUE
 # GOOGLE_API_KEY=PASTE_YOUR_ACTUAL_EXPRESS_MODE_API_KEY_HERE
 from google.adk.memory import VertexAiMemoryBankService
 

diff --git a/docs/integrations/galileo.md b/docs/integrations/galileo.md
@@ -38,7 +38,7 @@ Configure environment variables:
 
 ```env title="my_agent/.env"
 # Gemini environment variables
-GOOGLE_GENAI_USE_VERTEXAI=0
+GOOGLE_GENAI_USE_ENTERPRISE=0
 GOOGLE_API_KEY="YOUR_API_KEY"
 
 # Galileo environment variables

diff --git a/docs/streaming/dev-guide/part1.md b/docs/streaming/dev-guide/part1.md
@@ -206,18 +206,18 @@ One of ADK's most powerful features is its transparent support for both [Gemini
 
 #### How Platform Selection Works
 
-ADK uses the `GOOGLE_GENAI_USE_VERTEXAI` environment variable to determine which Live API platform to use:
+ADK uses the `GOOGLE_GENAI_USE_ENTERPRISE` environment variable to determine which Live API platform to use:
 
-- `GOOGLE_GENAI_USE_VERTEXAI=FALSE` (or not set): Uses Gemini Live API via Google AI Studio
-- `GOOGLE_GENAI_USE_VERTEXAI=TRUE`: Uses Gemini Live API (Agent Platform) via Google Cloud
+- `GOOGLE_GENAI_USE_ENTERPRISE=FALSE` (or not set): Uses Gemini Live API via Google AI Studio
+- `GOOGLE_GENAI_USE_ENTERPRISE=TRUE`: Uses Gemini Live API (Agent Platform) via Google Cloud
 
 This environment variable is read by the underlying `google-genai` SDK when ADK creates the LLM connection. No code changes are needed when switching platforms—only environment configuration changes.
 
 ##### Development Phase: Gemini Live API (Google AI Studio)
 
 ```bash
 # .env.development
-GOOGLE_GENAI_USE_VERTEXAI=FALSE
+GOOGLE_GENAI_USE_ENTERPRISE=FALSE
 GOOGLE_API_KEY=your_api_key_here
 ```
 
@@ -232,7 +232,7 @@ GOOGLE_API_KEY=your_api_key_here
 
 ```bash
 # .env.production
-GOOGLE_GENAI_USE_VERTEXAI=TRUE
+GOOGLE_GENAI_USE_ENTERPRISE=TRUE
 GOOGLE_CLOUD_PROJECT=your_project_id
 GOOGLE_CLOUD_LOCATION=us-central1
 ```

diff --git a/docs/streaming/streaming-tools.md b/docs/streaming/streaming-tools.md
@@ -68,7 +68,7 @@ Now let's define an agent that can monitor stock price changes and monitor the v
     ) -> AsyncGenerator[str, None]:
       """Monitor how many people are in the video streams."""
       print("start monitor_video_stream!")
-      client = Client(vertexai=False)
+      client = Client(enterprise=False)
       prompt_text = (
           "Count the number of people in this image. Just respond with a numeric"
           " number."

diff --git a/docs/tutorials/agent-team.md b/docs/tutorials/agent-team.md
@@ -117,7 +117,7 @@ print(f"OpenAI API Key set: {'Yes' if os.environ.get('OPENAI_API_KEY') and os.en
 print(f"Anthropic API Key set: {'Yes' if os.environ.get('ANTHROPIC_API_KEY') and os.environ['ANTHROPIC_API_KEY'] != 'YOUR_ANTHROPIC_API_KEY' else 'No (REPLACE PLACEHOLDER!)'}")
 
 # Configure ADK to use API keys directly (not Agent Platform for this multi-model setup)
-os.environ["GOOGLE_GENAI_USE_VERTEXAI"] = "False"
+os.environ["GOOGLE_GENAI_USE_ENTERPRISE"] = "False"
 
 
 # @markdown **Security Note:** It's best practice to manage API keys securely (e.g., using Colab Secrets or environment variables) rather than hardcoding them directly in the notebook. Replace the placeholder strings above.