google-genai

GenAI Python SDK

google-genai Permissive license Apache-2.0 Active ★ 3,920 v2.18.0 released 2026-08-13

Install

google-genai on PyPI

pip

pip install google-genai

uv

uv add google-genai

poetry

poetry add google-genai

Package facts

License	Apache-2.0 (permissive)
Python support	supports the current Python release (>=3.10)
Install friction	low — pure-Python wheel
Runtime dependencies	10 — anyio, google-auth, httpx, pydantic, requests, tenacity, websockets, typing-extensions, distro, sniffio
Maintenance	actively maintained — 0 days since the last release
Last repo commit	2026-08-13
First released	2024-12-10
Popularity	one of the top 1,000 most-downloaded packages on PyPI (30-day window, as of 2026-08-13)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-13)

Evidence: google_genai-2.18.0-py3-none-any.whl

Intended Audience :: DevelopersOperating System :: OS IndependentProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: InternetTopic :: Software Development :: Libraries :: Python Modules

About google-genai

from the package's own PyPI description — quoted content, verbatim

Google Gen AI SDK

PyPI version (image) Python support (image) PyPI - Downloads (image)

Documentation: https://googleapis.github.io/python-genai/

Google Gen AI Python SDK provides an interface for developers to integrate Google's generative models into their Python applications. It supports the Gemini Developer API and Gemini Enterprise Agent Platform APIs.

> [!WARNING] > Updates to Automatic Function Calling (AFC) in upcoming SDK version: > We are changing AFC behavior in the next major version. > Specifically, users will not be able to > invoke AFC from direct calls to Models.generate_content or its stream and > async variants. Instead, users should invoke AFC from Chats modules. > > | Methods/fields to be removed | migration guide | > | --- | --- | > | Live.send | Use send_client_content, send_realtime_input, or...

Read as markdown · JSON record · Source repository · Homepage

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

Google Gen AI SDK provides a Python interface to integrate Google's generative models, including Gemini APIs, into applications for content generation, chat, and agent-based interactions.

Low friction installation with a pure-Python wheel and well-maintained active status. Ten runtime dependencies (anyio, google-auth, httpx, pydantic, requests, tenacity, websockets, typing-extensions, distro, sniffio) are all established libraries, and the package was last updated 2026-08-13 with active repository maintenance.

Apache-2.0 permissive license allows commercial and private use with minimal restrictions, requiring only license and copyright notice preservation.

Usage

pip install google-genai

from google import genai

client = genai.Client(api_key='GEMINI_API_KEY')
response = client.models.generate_content(
    model='gemini-2.5-flash',
    contents='Why is the sky blue?'
)
print(response.text)

Requires a valid Gemini API key (GEMINI_API_KEY or GOOGLE_API_KEY environment variable) or Google Cloud project credentials for enterprise use.

Verdict: Active, well-maintained SDK with low install friction and no known vulnerabilities. Apache-2.0 licensing is permissive. Supports Python 3.10–3.14 and integrates cleanly via established dependencies. Suitable for production use, though note the upcoming 3.0.0 breaking changes to Automatic Function Calling and Live APIs documented in the package description.

Needs verification

Whether the ten runtime dependencies introduce any transitive security concerns or version conflicts in specific deployment environments.
Performance characteristics and rate-limiting behavior when used at scale with the Gemini APIs.
Stability guarantees for the beta API endpoints (default) versus v1 stable endpoints.

gemini api python clientgoogle generative ai sdkllm integration pythongoogle ai models pythongemini enterprise agent platformpython genai librarygoogle generative models