Devtoolwatch BoardGet it every Monday

Google Gen AI SDK review

Google Gen AI SDK is a Python library for integrating Google's generative models into applications through the Gemini Developer API or Gemini Enterprise Agent Platform.

Updated Nov 1, 2026. Review written Oct 22, 2026 from the project's own sources; usage data refreshed every Monday.

TL;DR

Google Gen AI SDK is Google's Python SDK for calling Gemini models from Python applications. It is for developers using either the Gemini Developer API with an API key or Gemini Enterprise Agent Platform with a Google Cloud project. One client covers text, image and audio generation, file uploads, function calling, and sync or async use.

Google Gen AI SDK at a glance

Category
Model SDKs and gateways
Maintained by
Google APIs (organization, @googleapis on GitHub)
License
Apache 2.0
Language
Python
Repository
github.com/googleapis/python-genai
Website
googleapis.github.io/python-genai
npm package
@google/genai 2.30.0
PyPI package
google-genai 2.32.0
Latest release
v2.32.0 on GitHub, Oct 21, 2026
First published
Dec 6, 2024

What Google Gen AI SDK does

  • Google Gen AI SDK generates content from Gemini models with text input and text output through client.models.generate_content.
  • Google Gen AI SDK can request image output or audio and speech output by setting response modalities in GenerateContentConfig.
  • Google Gen AI SDK uploads files and uses them in prompts on the Gemini Developer API.
  • Google Gen AI SDK accepts parameters as Pydantic models from google.genai.types or as plain dictionaries.
  • Google Gen AI SDK provides sync and async clients, with context managers that close the underlying HTTP connections.
  • Google Gen AI SDK supports function call parts, automatic function calling through Chats, and a Live API module.
  • Google Gen AI SDK lets you select API versions such as v1 or v1alpha and set proxies or a custom base URL.

How it works

Google Gen AI SDK runs inside your Python code. You create a genai.Client with an API key for the Gemini Developer API, or with enterprise=True, a project and a location for Agent Platform. Environment variables can supply these settings instead. The SDK calls beta API endpoints by default and uses httpx for HTTP, with aiohttp available as an optional async backend.

How to install and start using Google Gen AI SDK

With pip

pip install google-genai

With uv

uv pip install google-genai

Requirements

  • Python 3.10 or later.
  • A Gemini API key (GEMINI_API_KEY or GOOGLE_API_KEY) for the Gemini Developer API.
  • A Google Cloud project ID and location for Gemini Enterprise Agent Platform.

First steps

  1. Install the package, then import it with from google import genai and from google.genai import types.
  2. Set GEMINI_API_KEY, or set GOOGLE_GENAI_USE_ENTERPRISE, GOOGLE_CLOUD_PROJECT and GOOGLE_CLOUD_LOCATION for Agent Platform.
  3. Create a client with genai.Client(), then call client.models.generate_content with a model such as gemini-flash-latest.
  4. Close the client with client.close(), or use a with block so the client closes automatically.

Who Google Gen AI SDK is for

  • Teams that may move between the Gemini Developer API and Gemini Enterprise Agent Platform using one client.
  • Async Python services that need an async client, with optional aiohttp for faster performance.

Limitations to know

  • Google Gen AI SDK's next major version changes automatic function calling and removes several Live and Models fields. Pin to < 3.0.0 to avoid this.
  • Google Gen AI SDK's file upload example is marked as available on the Gemini Developer API only.
  • Google Gen AI SDK uses beta API endpoints by default. Stable endpoints require setting the API version to v1.
  • Google Gen AI SDK only works with Google's generative models through Google's APIs.

Is Google Gen AI SDK growing? Usage data

In the week of Oct 25–31, 2026, Google Gen AI SDK ranked #250 on the Devtoolwatch Board and #14 in Model SDKs and gateways, with a momentum score of 38 out of 100. Its main package had about 67.8M downloads that week, +4% against its own 4-week average.

New GitHub stars per week for Google Gen AI SDK12 weeks from Aug 9, 2026: 20, 16, 16, 14, 13, 14, 14, 13, 16, 16, 17, 11 new stars, an average of 15 a week.Aug 9week of Oct 25
New GitHub stars per week for the last 12 weeks, from GitHub's stargazer history (today's stargazers by the week they starred).
Show the weekly numbers
New GitHub stars per week for Google Gen AI SDK
Week ofNew stars
Aug 9, 202620
Aug 16, 202616
Aug 23, 202616
Aug 30, 202614
Sep 6, 202613
Sep 13, 202614
Sep 20, 202614
Sep 27, 202613
Oct 4, 202616
Oct 11, 202616
Oct 18, 202617
Oct 25, 202611

The Board ranks tools by four signals each week: new stars, new stars for the repo's size, added downloads and download growth beyond the market. How the ranking works.

Google Gen AI SDK alternatives

Other LLM SDKs and gateways on the Board in the week of Oct 25–31, 2026, by momentum:

Model SDKs and gateways ranked by momentum, the week of Oct 25–31, 2026
RankToolStarsDownloads/wk
#1thinking-orbsthinking-orbs is a React library of dotted, animated thought-orb loading indicators for AI and agent user interfaces.3.9k1.4M
#2HeadroomHeadroom compresses tool outputs, logs, files, and RAG chunks locally before they reach the LLM, as a library, proxy, or MCP server.78.5k125.8k
#3LiteLLMLiteLLM is an open source AI gateway and Python SDK that calls 100+ LLM providers through one OpenAI-format interface.62.5k23.1M
#4Honcho Memory library for building stateful agents7.9k–
#5Anthropic SDKAnthropic SDK is the official Python library for calling the Claude API from Python applications.4k111M
#6Hugging Face HubHugging Face Hub is the official CLI and Python client for downloading, uploading and managing models, datasets and Spaces on the…4k68.3M

All LLM SDKs and gateways, ranked

Recent Google Gen AI SDK releases

Google Gen AI SDK FAQ

Is Google Gen AI SDK free and open source?

Yes. Google Gen AI SDK's source code is on GitHub (googleapis/python-genai) under the Apache 2.0 license, so you can use it for free.

How do I install Google Gen AI SDK?

Run pip install google-genai. It needs Node.js >=20.0.0. The install section above has the other options from the project's README.

Is Google Gen AI SDK still maintained?

Yes. The googleapis/python-genai repository was last updated on Oct 21, 2026, and the latest release, v2.32.0 on GitHub, came out on Oct 21, 2026.

How popular is Google Gen AI SDK?

Google Gen AI SDK has 4k GitHub stars as of Nov 1, 2026. It gained 11 new stars in the week of Oct 25–31, 2026, against a 12-week average of 15 a week. Its main package had about 67.8M downloads that week, +4% against its own 4-week average. That made it #14 among LLM SDKs and gateways on the Devtoolwatch Board.

What are the best alternatives to Google Gen AI SDK?

Other LLM SDKs and gateways on the Devtoolwatch Board in the week of Oct 25–31, 2026, by momentum: thinking-orbs (#1), Headroom (#2), LiteLLM (#3), Honcho (#4), Anthropic SDK (#5). The alternatives table above has their numbers.

What is Google Gen AI SDK?

Google Gen AI SDK is a Python library from Google for integrating Google's generative models into Python applications. It supports the Gemini Developer API and Gemini Enterprise Agent Platform APIs.

Is there a Google Gen AI SDK for JavaScript and TypeScript?

Yes. Google publishes a related npm package, @google/genai, which requires Node.js 20.0.0 or later. This repository covers the Python SDK.

Where is the Google Gen AI SDK documentation?

The Google Gen AI SDK documentation is at https://googleapis.github.io/python-genai/. It includes modules for client, live, models, tokens, tunings and types.

How does Google Gen AI SDK authenticate?

Google Gen AI SDK uses an API key for the Gemini Developer API, passed to the client or read from GEMINI_API_KEY or GOOGLE_API_KEY. For Agent Platform, it uses a project and location. If both key variables are set, GOOGLE_API_KEY takes precedence.

Can Google Gen AI SDK help AI coding assistants write correct code?

Yes. The README recommends loading Gemini API Skills into assistants such as Claude Code or Cursor. The skills come from google-gemini/gemini-skills for the Developer API, or google/skills for Agent Platform.

Does Google Gen AI SDK work behind a proxy?

Yes. Google Gen AI SDK reads proxy settings such as HTTPS_PROXY from environment variables. It supports socks5 through httpx[socks] and accepts a custom base URL for API gateway proxies.

Sources

  1. googleapis/python-genai on GitHub
  2. Google Gen AI SDK README
  3. @google/genai on npm
  4. google-genai on PyPI
  5. Google Gen AI SDK website
  6. Release v2.32.0 (Oct 21, 2026)
  7. Release v2.31.0 (Oct 14, 2026)
  8. Release v2.30.1 (Oct 13, 2026)
  9. Devtoolwatch Board, the week of Oct 25–31, 2026

Google Gen AI SDK README badge

Maintainers can show the tool's weekly Board rank in their README:

Devtoolwatch badge for Google Gen AI SDK

[![Devtoolwatch](https://index.devtoolwatch.com/badge/google-genai.svg)](https://index.devtoolwatch.com/tools/google-genai/)

How this page is made: Devtoolwatch writes each review from the project's README, releases, package metadata and website, with an AI model, then checks every claim against the source it cites and drops what the sources don't support. The numbers come from Devtoolwatch's daily GitHub snapshots, GitHub's stargazer history, and the npm and PyPI download APIs. Spotted an error? Email [email protected].