python-genai v3.3.0
Adds XHIGH thinking level, missing enum values, and gemini-4-hydrogen model enum.
The Deploy Log | Products | Free, no signup
python-genai changelog
6 versions of python-genai from Google in The Deploy Log. From to . On the median a new version every 8 days, publisher's dates only; the longest wait was 19 days. The newest is v3.3.0. 4 versions in the last 30 days. Each links the publisher's own page.
| Version | Publisher's date | Days after the one before |
|---|---|---|
| v3.3.0 | 2 | |
| v3.1.0 | 12 | |
| v2.34.0 | 8 | |
| v2.32.0 | 19 | |
| v2.28.0 | 1 | |
| v2.27.0 |
python-genai v3.1.0
Adds gemini-omni-1.2-flash as the gemini-api video default, proactive_video for Live API, xhigh thinking level, and usage_metadata for Gemini Enterprise API.
python-genai v2.34.0
Adds continuation_token, video upscale, video understanding, and Python 3.15 support.
python-genai v2.32.0
python-genai v2.32.0 adds base_voice, generation_output_config, and Live API in-session context updates.
python-genai v2.28.0
Adds lyria-3.5, gemini-omni-1.1-flash, and gemini-omni-flash-preview to the Interactions Model enum and supports continuation_token.
python-genai v2.27.0
python-genai v2.27.0 adds support for continuation_token in GenerateContent.
One line every time AI actually ships, around the clock, free on Threads and Bluesky. Every one is in The Deploy Log with its source.