On this page
01
Call Gemini through the same governed endpoint
Connect your Vertex AI / Gemini credentials once via BYOK. Apps then call the same OpenAI- or Anthropic-compatible endpoint and just set the model — the gateway routes by model and policy, so no provider keys live in app code.
python
from openai import OpenAI
client = OpenAI(base_url="https://api.cloptima.ai/v1/ai", api_key="clop_vk_dPXO67p…")
resp = client.chat.completions.create(
model="gemini-3.8-flash", # approved Gemini/Vertex model (Cloptima maps to the provider id)
messages=[{"role": "user", "content": "..."}],
extra_headers={"x-cloptima-team": "data", "x-cloptima-app": "insights", "x-cloptima-environment": "production"},
)02
Attribute every call
Attach team, app, customer, workflow, and run metadata so Gemini and Vertex spend can be compared directly with your other providers.
03
Govern and report
Set model allowlists, environment limits, and budgets for Gemini usage, and keep attributed records to report spend across teams and apps.