Gemini 3 Flash Agent

Model pricing

Prices are shown per 1M tokens alongside their official reference rates. Your customer portal is authoritative for actual kineticRouter billing.

Variant pricing uses the official gemini-3-flash-preview base-model rates.

API example

Use the OpenAI-compatible kineticRouter route with Gemini 3 Flash Agent.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.kineticrouter.com/v1",
    api_key=os.environ["KINETICROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="gemini/gemini-3-flash-agent",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

About this model

Gemini 3 Flash Agent through the OpenAI-compatible kineticRouter API.