Install Gemini 3 Pro API SDK for Python and Node.js with pip and npm
If you’re a developer looking to play with Gemini 3 Pro’s language features, the first thing you’ll probably do is grab the right client library for the environment you already have - say a Python notebook or a Node.js service. It isn’t just “read the docs” and hope for the best; the API works on a usage-based pricing model, so each request shows up on your bill. That’s why Google ships official SDKs that take care of auth, request formatting and response parsing, sparing you the hassle of hand-coding HTTP calls.
Once you install the appropriate package, you can spend more time crafting prompts and handling the output instead of wrestling with low-level details. The next thing to watch out for is keeping your API key out of the source code - a sensible move for any pay-per-call service. Below are the exact commands to add the SDKs to your project and a quick tip on where to stash the required key safely.
Choose your preferred language and install the official SDK using following commands: Python: pip install google-genai Node.js/JavaScript: npm install @google/genai Store your API key securely in an environment variable: export GEMINI_API_KEY="your-api-key-here" The Gemini 3 Pro API utilizes a pay-as-you-go model, where your costs are primarily calculated based on the number of tokens consumed for both your input (prompts) and the model's output (responses). The key determinant for the pricing tier is the context window length of your request. Longer context windows, which allow the model to process more information simultaneously (like large documents or long conversation histories), incur a higher rate.
The following rates apply to the gemini-3-pro-preview model via the Gemini API and are measured per one million tokens (1M). The API presents several revolutionary parameters one of which is the thinking level parameter, giving full control over to the requester in a very detailed manner.
Will developers adopt it? The Gemini 3 Pro SDK ships for Python and Node.js, and you can grab it with a single command. In Python run pip install google-genai; in JavaScript do npm install @google/genai.
Then drop your key into an environment variable, e.g. export GEMINI_API_KEY="your-api-key-here". Some folks like the env-var trick because it’s quick, while others will probably reach for a secret-manager to keep things locked down.
Google says the model can create, reason and understand multimodal input, and it even adds agent-like features that might make building smart apps easier. The article, however, doesn’t give any speed or quality numbers, so it’s hard to say how it stacks up against what we already have. Pricing is only hinted at with a vague “pay-a” line, leaving the cost side pretty fuzzy.
You can start playing with it right now, but keep an eye on usage caps and billing once the docs are fleshed out. In short, getting it running is simple; whether it will change our workflow depends on how those promised abilities hold up in practice.
Related Reading
Browse all Google news →
LLMs & Generative AI OpenAI says AI saves knowledge workers 40‑80 minutes; use yields five‑fold gains
LLMs & Generative AI Grok Chat: AI for debugging, building, testing web apps with voice and images
LLMs & Generative AI Samsung adds Vision AI Companion, an AI Bixby, to TVs for real‑time queries
Related Topic Google AI lets shoppers call stores, browse 50 B listings, get side‑by‑side charts
AI Tools & Apps
Related Topic Google expands AI partnership with Tel Aviv University, infrastructure for Gemma
Research & Benchmarks
Common Questions Answered
How do I install the Gemini 3 Pro SDK for Python?
You can install the official Gemini 3 Pro Python SDK by running the command `pip install google-genai` in your terminal. This single pip command pulls the client library and its dependencies, allowing you to start making API calls from a Python notebook or script.
What command should I use to add the Gemini 3 Pro SDK to a Node.js project?
For a Node.js or JavaScript backend, install the SDK with `npm install @google/genai`. This npm command adds the @google/genai package to your project's dependencies, enabling you to import and use the Gemini 3 Pro client in your code.
How should I securely provide my Gemini 3 Pro API key to the SDK?
Store the API key in an environment variable, for example by running `export GEMINI_API_KEY="your-api-key-here"` in your shell before starting your application. Both the Python and Node.js SDKs automatically read this variable, keeping the key out of source code.
What pricing model does the Gemini 3 Pro API use and how are costs calculated?
The Gemini 3 Pro API follows a pay‑as‑you‑go model where you are billed based on the number of tokens processed. Costs are incurred for both input tokens (your prompts) and output tokens (the model's responses), so larger requests result in higher charges.
Can I use secret‑management tools instead of environment variables for the Gemini 3 Pro API key?
Yes, while the article highlights the convenience of setting `GEMINI_API_KEY` as an environment variable, developers can also integrate secret‑management solutions like Vault, AWS Secrets Manager, or GCP Secret Manager for added security. These tools allow the SDK to retrieve the key programmatically without exposing it in plain text.