Gemini 3 Pro now available in Gemini CLI
we have integrated gemini 3 proOur most intelligent model, directly into the Gemini CLI to unlock a new level of performance and productivity in the terminal. This powerful combination provides cutting-edge logic to better execute commands, increases support for complex engineering work through agentic coding, and enables smarter, more tailored workflows through advanced tool utilization.
To ensure the experience remains fast and reliable, we’re gradually rolling out access.
- Gemini 3 Pro is available now in Gemini CLI google ai ultra For customers and for those who have access through payment Gemini API Key.
- For Gemini Code Assist Enterprise Users, access is coming soon.
- All other users, Users of Google AI Pro, Gemini Code Assist Standard, and the free tier can join the waitlist here to gain access as soon as it becomes available.
You can also track our rollout progress by following this GitHub discussion.
Get started using Gemini 3 Pro with Gemini CLI
If you’re a Google AI Ultra customer or have a paid Gemini API key, get started right away by upgrading your Gemini CLI version 0.16.x,
npm install -g @google/gemini-cli@latestshell
After confirming your version, run /settingstoggle again Preview Features To TruthGemini CLI will now be the default on Gemini 3 Pro,
Users can follow the instructions in this video to know how to enable Gemini 3 Pro in Gemini CLI
Here are 5 practical ways you can use Gemini 3 Pro in the Gemini CLI to accelerate development and bring your biggest ideas to life.
Create anything in Terminal with better agentive coding
The Gemini 3 Pro excels at coding due to its ability to synthesize disparate pieces of information including text, images and code, and follow complex, creative instructions. It captures the intention behind your idea, allowing you to go from a raw concept to a functional starting point in a single step.
- Generate a ready-to-deploy app with 3D graphics
Gemini 3 Pro’s agentive coding capability allows it to handle signals that are both a creative brief and a technical specification at the same time. It can take a prompt, create a detailed execution plan, and then create the entire scaffold for a runnable web project, not just a single file.
For example, let’s say you have an idea for a visually impressive prototype – a 3D graphic for a landing page or a quick tech demo. Instead of spending hours setting up graphics libraries and a local dev server, you can describe the entire project at once and immediately have a working starting point.
Objective: Build a visually stunning, photorealistic 3D Voxel simulation of the Golden Gate Bridge using Three.js, prioritizing quality and complex visuals (no simple blocks), atmospheric depth and 60FPS performance.
Visuals & Atmosphere:
- Lighting: Slider (0-24h) controlling sun position, light intensity, sky color, and fog color.
- Fog: Volumetric-style fog using sprite particles that drift and bob. Slider 0-100. 0 = True Zero (Crystal Clear). 100 = Dense but realistic (not whiteout).
- Water: Custom GLSL shader with waves, specular reflections, and manual distance-based fog blending (exp2) for seamless horizon integration.
- Post-Processing: ACESFilmic Tone Mapping and UnrealBloom (optimized for glowing lights at night).
Scene Details:
- Bridge: Art Deco towers with concrete piers (anchored to seabed), main span catenary cables, and suspenders.
- Terrain: Low-poly Marin Headlands and SF Peninsula.
- Skyline: Procedural city blocks on the SF side.
- Traffic: Up to 400 cars using `InstancedMesh`, positioned accurately on top of the deck (ensure vertical alignment prevents clipping into the concrete). Each car features emissive headlights (white) and taillights (red).
- Ships: Procedural cargo ships with hull, containers, and functional navigation lights (Port/Starboard/Mast/Cabin) moving along the water.
- Nature: Animated flocking birds.
- Night Mode: At night, activate city lights, car headlights, ship navigation lights, tower beacons, street lights.
Tech & Controls:
- Core: Must output only single HTML file `golden_gate_bridge.html` to be run in a blank Chrome tab. Import Three.js/Addons via CDN map.
- `three` (Core library) via CDN (ES Modules).
- `three/examples/jsm/...` modules via Import Map.
- No build step (Vite/Webpack). Pure HTML/JS.
- UI: Visually appealing sliders for Time (0-24h), Fog Density (0-100%), Traffic Density (0-100%), and Camera Zoom.
- Optimization: `InstancedMesh` for all repetitive elements (cars, lights, birds).plain text
2. Turn a visual idea into a working app
You’ve sketched a UI and need to translate that visual concept into functional code. You can take a photo of your sketch, and then drag and drop the image file into your terminal.
Gemini 3 Pro’s multimodal understanding will analyze the identity of drawings, buttons, text boxes and layouts. It then generates HTML, CSS, and JavaScript code to bring your sketch to life.
Create a UI for "Project Constellation," an internal brand intelligence tool prototype that shows a customer acquisition pipeline. The aesthetic is an ultra-creative, futuristic dark-mode nebula. Luminous, iridescent threads representing customer journeys weave through semi-transparent glass pillars. A sleek, floating data card with Tailwind CSS precision materializes when hovering over a pillar. I've prepared a sketch for you to work from: @sketch.png.plain text
improve your daily routine
While vibe coding demos show the art of the possible, the true test of a developer tool is how it handles the practical, everyday work you do multiple times a day. Small improvements to these common workflows, such as refactoring code, debugging errors, or managing infrastructure, create real productivity gains.
This is where the Gemini 3 Pro’s cutting-edge logic makes a tangible difference. It follows the nuances of complex, multi-part orders with greater accuracy than ever before, which is essential for the practical, detailed work that defines your day.
Here are some examples of how the Gemini 3 Pro can handle these important engineering tasks.
3. Generate complex shell commands with natural language
With the Gemini CLI, the power of the Unix command line is available directly through natural language. There’s no need to remember obscure syntax and every flag of a UNIX command, just let Gemini 3 Pro translate your intent and execute it for you. Gemini can then also parse the densely formatted output into natural language for you.
Ask the Gemini CLI to handle all the complexities of running git bisect for you on the command line, leaving you free to focus on implementing your decision on finding the bug in question.
At some point I lost the commit that set my default theme to dark.
Find it for me with git bisect and return the hash to me.plain text
4. Generate accurate documentation from your code
Gemini 3 Pro’s advanced logic allows it to read and understand the logic of your codebase. It doesn’t just look at syntax; It can examine and synthesize the purpose of a function, identify its parameters and return values, and translate that complex logic into clear, human-readable language.
This is useful when you have introduced a complex application and now need to create documentation. Instead of manually writing the details, you can have Gemini analyze the code and generate documentation for you in a format that suits your code.
"This is an application that does not have any documentation and we do not have a technical writer. Before you begin, review all of the code. Then make me a user documentation. This document should only explain user facing features, but make sure to explain every single feature such as usage of the app, command line options, authentication options, built in tools, and all other user facing features. For certain features such as MCP or extensions, also explain the topic and concept so that the user has a better understanding. Since this is an open source project, provide an architectural overview of how the code is laid out, a summary of each component, and how they can contribute to the open-source project. The document should be organized and formatted so that it is easy to read and find. Do not make it a single html page. Make sure to add a search feature."plain text
5. Debug performance issue in Live Cloud Run service
Gemini 3 Pro can streamline complex workflows across different services that take into account the context of your team. Improved tool utilization means it can plan and execute multi-step tasks that require gathering information from multiple sources – such as observation, security and source control – to solve a single problem.
In this example it combines a serverless platform (Cloud Run) with a popular security scanner (Snyk), detects the root cause using the Gemini CLI extension and suggests a solution, then deploys the fix, turning a complex, multi-tool investigation into a single, streamlined action.
Users are reporting that the "Save Changes" button is slow, investigate the 'tech-stack' serviceplain text
Learn more today
These examples are just the beginning. The real potential isn’t in running these specific commands, but in how Gemini 3 Pro can adapt to your unique challenges, whether you’re customizing daily shell commands, tackling substantial engineering work, or building personalized workflows for your team’s tools. Gemini 3 Pro turns the command line into an intelligent partner that understands your context.
The best way to see the difference is to try it yourself. Visit the Gemini CLI website, and share your examples on social media with #GeminiCLI. We can’t wait to see what you create.