Tabbit
ResourcesBlogModels
Tabbit LogoTabbit

Tabbit — The AI Browser that Works for You

Topics

  • Best Browsers 2026: Rankings and Top Lists
  • AI Browser Guides and Resources
  • Browser Comparisons: Head-to-Head Guides
  • Browser Reviews and Explainers
  • Browser Alternatives
  • Browser Directory: Guides by Browser
  • Agentic Browser Resources
  • Browser Downloads and Install Guides
  • Browser Productivity Resources
  • SillyTavern Model Guides and Presets

Popular Guides

  • Best Browsers 2026: Top 10 Ranked & Compared
  • Best Free AI Browsers 2026: Plans & Prices Compared
  • Rabbit Browser: What It Is & Why Tabbit Is Better
  • Firefox vs Chrome 2026: Privacy, RAM & Speed Compared
  • Best Lightweight Browsers 2026: 7 Tested for RAM & Speed
  • AI Browser List 2026: 10 Browsers Compared
  • Neobrowser: Norton Neo, Download & Alternatives
  • Edge vs Chrome 2026: Speed, RAM & Battery Tested
  • Best Internet Browser for Android 2026
  • Best AI Browser 2026: Top 9 Tested & Ranked

Events

  • Tabbit Skill Competition
  • KPOP SBTI Fandom Personality Test
  • Tabbit Campus Creator Program
  • fifi's Picks: AI Skills for Research Papers
  • User Survey

About

  • Tabbit Blog
  • Press & Media
English
简体中文English
Showcases & prompts
MediaGemini 4 Carbon

Google Cloud Gemini Enterprise: Configure Enterprise Access to Gemini 4 Carbon

Original source

Google Cloud Gemini Enterprise

AuthorNot specified

Source date2026-11-12

Tabbit curation2026-11-12

Read original

One-sentence takeaway

In Gemini Enterprise, Carbon is available by default to users with a valid enterprise developer seat, provided the administrator has not configured a custom model allowlist. If an allowlist is configured, the administrator must explicitly add Gemini 4 Carbon. Model visibility also requires the user to have the Gemini Enterprise User IAM role and to use a supported Antigravity client in the correct project and location where AI developer tools are enabled.

Use cases

  • Suitable tasks: Enabling or restricting developers' access to Gemini 4 Carbon in Antigravity within an organization.

  • Unsuitable tasks: Configuring the Gemini API, personal Google AI Studio accounts, or consumer Google AI subscriptions. They do not use the Gemini Enterprise project seat and Antigravity authorization model settings described here.

  • Applicable model version: Gemini 4 Carbon (listed in Google Cloud documentation as a model supported by AI developer tools).

  • Applicable client, agent, or API: AI developer tool settings in the Gemini Enterprise Admin console; the Antigravity app, CLI, or a supported IDE client.

  • Recommended reasoning level and parameters: Not specified. This article configures enterprise access and does not cover model inference parameters.

Ready-to-use content

Access requirements

Check each of the following conditions:

Carbon is available
= an eligible Gemini Enterprise subscription and an active developer seat
  + the user has the Gemini Enterprise User IAM role
  + AI developer tools are enabled for the selected Google Cloud project and location
  + the Antigravity authorized models field is empty, or the custom list includes Gemini 4 Carbon

Google's documentation lists Gemini Enterprise Standard, Plus, Standard Emerging Markets, and Pay-as-you-go as subscriptions that include AI developer tools. Standard Emerging Markets is available only to eligible customers. The documentation defines a "licensed user" as a developer with an active Gemini Enterprise seat. An administrator role alone does not grant developer access.

Carbon's default authorization rules

  • Antigravity authorized models is left empty: All supported Gemini models are allowed. Gemini 4 Carbon is available by default to licensed users, and Google models released later are automatically added to the available set.

  • Antigravity authorized models is set to a custom list: Only models on the list are available. The administrator must select Gemini 4 Carbon in the list. Newly released or unselected models are not automatically enabled.

  • Third-party models: Disabled by default and require separate administrator enablement. This does not affect the Google model authorization rules for Carbon described above.

Administrator setup steps

  1. Confirm that the Google Cloud project is linked to an eligible Cloud Billing account and has a supported Gemini Enterprise subscription with seats available for assignment.

  2. Assign seats to developers who need the tools and grant them the project-level Gemini Enterprise User role (roles/discoveryengine.agentspaceUser). The administrator performing the setup needs the Gemini Enterprise Admin role (roles/discoveryengine.agentspaceAdmin).

  3. In the Google Cloud console, open Gemini Enterprise → Settings → AI developer tools. New subscriptions are enabled by default where the tool is supported in the purchase region. For existing subscriptions, an administrator must enable it manually for each location (global, us, or eu).

  4. Under Model availability, click Edit and check Antigravity authorized models. Leave it empty to allow all supported Gemini models, or set a custom list and select Gemini 4 Carbon, then save.

  5. Developers should sign in using the project and location to which their seat is assigned and use an enterprise-supported Antigravity client.

When AI developer tools are enabled, the console checks the configuration and automatically enables the required Discovery Engine API and Business AI Code API. Enabling the APIs does not grant users access. The correct IAM role and seat are still required.

Testing or workflow steps

  1. Sign in to Antigravity with a developer account that has an assigned seat and confirm that the correct project and location are selected.

  2. Leave the authorized models field empty and confirm that Carbon is available to that user in the model picker.

  3. Change authorized models to a custom list and remove Carbon, then confirm that the user cannot select Carbon. Add Carbon back, save, and check the model picker again.

  4. Check an account without an assigned seat or without the Gemini Enterprise User role. Confirm that enabling the tool or having an administrator role alone does not replace user authorization.

This is an administrator acceptance workflow derived from the rules described in the documentation. It is not a record of configuration or verification in an actual Google Cloud project.

Original evidence and data

  • The documentation's "Configure authorized models" section says that leaving the authorized models field empty allows all supported Gemini models. Once one or more models are selected, only the selected models are allowed, and unselected or newly released models must be added manually by an administrator.

  • The "Supported models" section explicitly lists Gemini 4 Carbon and says that, with the default model selection enabled (an empty list), it is available by default to licensed users. With a custom list, it must be selected manually.

  • The documentation defines a licensed user as a developer holding a seat license for Gemini Enterprise Standard, Plus, or Pay-as-you-go.

  • The "Prerequisites" section says that configuring AI developer tools requires the Gemini Enterprise Admin role. An administrator role alone does not grant access to the tools. Users must still be explicitly granted the Gemini Enterprise User role.

  • The documentation says existing subscriptions must have AI developer tools enabled manually for each location. New Standard, Plus, or Pay-as-you-go subscriptions are enabled by default when the tool is supported in the country or region of purchase.

  • The documentation says that the console checks for and automatically enables the required APIs when the tools are enabled, but enabling the APIs does not automatically grant users access.

Limitations

  • Gemini Enterprise tool access depends on the enterprise seat, project-level IAM, and Antigravity authorized model settings together. Consumer subscriptions such as Google AI Pro and Google AI Ultra are not among the enterprise seat types listed here and should not be treated as substitutes for a Gemini Enterprise seat or enterprise model authorization.

  • The documentation describes organization-level model authorization and user access prerequisites. It does not guarantee that a specific account, region, project, or billing status currently meets them. Check the administrator console and the organization's actual subscription.

  • Automatic access to newly released models applies only while the authorized models field remains at its default empty value. Administrators must maintain custom lists over time.

  • Google's documentation directs users to a separate Help Center for the Business edition. This article applies only to Standard, Plus, Pay-as-you-go, and eligible Standard Emerging Markets subscriptions described on that page.

Reproduction notes

Collection date: 2026-11-16. The full body was read from the Google Cloud official page, opened through the user-specified Tabbit browser task. The page lists its last updated date as 2026-11-12 (UTC). This article summarizes the prerequisites, default rules, and console steps in the official documentation. No external Google Cloud project was accessed or modified.

Curated by Tabbit

Prompts and showcases are summarized from public sources and Tabbit editorial notes. Check the original licensing and intended use before copying it.

Gemini 4 Carbon

Use in Tabbit

Gemini 4 Carbon

Related showcases & prompts

OfficialGoogle AI Studio / Gemini API

Google AI API Specifications for Gemini 4 Carbon

OfficialGoogle AI Studio / Gemini API

Gemini 4 Carbon Long Outputs: Continuation and Stop Conditions

OfficialGoogle AI Studio2026-11-10

Google AI Studio: Prompting Gemini 4 Carbon for Complex Tasks

OfficialGoogle AI Studio / Gemini API

Google AI Studio: Gemini 4 Carbon Agentic Video Understanding Configuration

Gemini 4 Carbon

Related reviews

OfficialGoogle DeepMind

Gemini 4 Carbon Model Card: Knowledge Work and Multimodal Benchmarks and Their Limits

MediaArtificial Analysis

Gemini 4 Carbon: Artificial Analysis Reasoning Tiers and Index Costs

MediaZapier

Gemini 4 Carbon on Zapier AutomationBench: Business Workflow Results

MediaAI IQ

Gemini 4 Carbon's Composite Score and Benchmark Coverage on AI IQ