Gemini API
Use Gemini models through one API, at a published rate, with usage on one monthly invoice alongside every other model. No separate Google account needed.
Gemini models and prices
| Model | Input / 1M | Output / 1M | Context | Best for | Processed in |
|---|---|---|---|---|---|
Gemini 3.1 Pro Google | $2.30 | $13.80 | 1.05M | Video, audio and long PDFs | Global |
Gemini 3.8 Flash Google | $0.8625 | $4.3125 | 1.05M | Coding agents at a mid-range price | Global |
Per million tokens, in US dollars, unless a row names another unit.
Which Gemini model to use
Near-flagship coding at Flash speed, and large volumes of video, audio and PDFs.
Questions across video, audio, images and long PDFs at once, and abstract reasoning and science problems.
Calling the Gemini API
The Roar AI gateway speaks the OpenAI API format. Point the OpenAI SDK at Roar AI and name a Gemini model; moving to another provider’s model later is a change to the model name.
from openai import OpenAI
client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")
reply = client.chat.completions.create(
model="gemini-3.8-flash",
messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)Where Gemini requests are processed
Gemini models are processed on international infrastructure. Your requests enter through the Roar AI gateway nearest you; the rest of the way, the route is the one we chose for each model, and it stays the same from call to call.
Questions
Can I use the Gemini API through Roar AI?
Yes. Every Gemini model listed on this page is available through Roar AI’s API, on the same key as every other model on the platform.
How is Gemini usage billed?
At the published rate per model, on one monthly invoice together with any other models your team uses. The rate does not move with what a provider charges us.
Do I need a separate account with Google?
No. One Roar AI key reaches every Gemini model listed here, so there is no separate Google account to set up.
Where are Gemini requests processed?
Gemini models are processed on international infrastructure. Your requests enter through the Roar AI gateway nearest you.
Gemini and every other model,
on one key
One key for every Gemini model and every other model, on one monthly invoice.