Safety_settings not working when using OpenAI compatibility extra body

Gemini API
,
1 
from openai import OpenAI

client = OpenAI(
    api_key=MY_API_KEY,
    base_url="https://generativelanguage.googleapis.com/v1beta/"
)

stream = client.chat.completions.create(
    model="gemini-2.5-pro-preview-03-25",
    n=1,
    messages=[
        {
            "role": "user",
            "content": "Summarize the video"
        }
    ],
    stream=True,
    stream_options={'include_usage': True},
    extra_body={
        'extra_body':
        {
            'google': {
              'cached_content': "cachedContents/0000aaaa1111bbbb2222cccc3333dddd4444eeee"
          }
        }
    }
)

for chunk in stream:
    print(chunk)
    print(chunk.usage.to_dict())

This is what the documentation at OpenAI compatibility  |  Gemini API  |  Google AI for Developers says. I tried replacing it with safety settings like:

“extra_body”: {
“google”: {
“safety_settings”: [
{“category”: “HARM_CATEGORY_HARASSMENT”, “threshold”: “BLOCK_NONE”},
{“category”: “HARM_CATEGORY_HATE_SPEECH”, “threshold”: “BLOCK_NONE”},
{“category”: “HARM_CATEGORY_SEXUALLY_EXPLICIT”, “threshold”: “BLOCK_MEDIUM_AND_ABOVE”},
{“category”: “HARM_CATEGORY_DANGEROUS_CONTENT”, “threshold”: “BLOCK_NONE”},
{“category”: “HARM_CATEGORY_CIVIC_INTEGRITY”, “threshold”: “BLOCK_NONE”}
]
}
}

And it does not work. Either the documentation is wrong or the backend implementation is not active yet.

3

Hi @aliencaoao , Welcome to the forum.

I have notified the engineering team about the issue. I will follow up with you once I have more information.

Thanks!

5

Just a heads up: the safety setting feature is not implemented yet in OAI Compatibility. We will update the doc to reflect that. Sorry about the documentation issue.