Use Gemini models through one API, with pricing in Sri Lankan rupees and usage on one monthly invoice. No separate Google account or foreign card needed.
| Model | Input / 1M | Output / 1M | Context | Best for | Processed in | |
|---|---|---|---|---|---|---|
| LKR 999 | LKR 4,995 | 1.05M | Finance, legal and long documents | Global | ||
| Cached input | LKR 49.95 | — | Repeat a long prompt prefix and those tokens bill at this rate. Automatic. | |||
| Batch | LKR 500 | LKR 2,498 | Results within 24 hours, for work nobody is waiting on. | |||
| Priority | LKR 1,798 | LKR 8,991 | Faster service, for something a person is sitting in front of. | |||
| Everything about Gemini 4 Neon | ||||||
| LKR 666 | LKR 3,330 | 1.05M | Finance, legal and research work | Global | ||
| Cached input | LKR 33.30 | — | Repeat a long prompt prefix and those tokens bill at this rate. Automatic. | |||
| Batch | LKR 333 | LKR 1,665 | Results within 24 hours, for work nobody is waiting on. | |||
| Priority | LKR 1,199 | LKR 5,994 | Faster service, for something a person is sitting in front of. | |||
| Everything about Gemini 4 Argon | ||||||
| LKR 666 | LKR 3,996 | 1.05M | Video, audio and long PDFs | Global | ||
| Cached input | LKR 66.60 | — | Repeat a long prompt prefix and those tokens bill at this rate. Automatic. | |||
| Batch | LKR 333 | LKR 1,998 | Results within 24 hours, for work nobody is waiting on. | |||
| Long requests | LKR 1,332 | LKR 5,994 | Above 200,000 input tokens, the whole request is billed at these rates. | |||
| Everything about Gemini 3.1 Pro | ||||||
| LKR 250 | LKR 1,249 | 1.05M | Coding agents at a mid-range price | Global | ||
| Cached input | LKR 24.98 | — | Repeat a long prompt prefix and those tokens bill at this rate. Automatic. | |||
| Batch | LKR 125 | LKR 624 | Results within 24 hours, for work nobody is waiting on. | |||
| Everything about Gemini 3.8 Flash | ||||||
Rupee prices are our published US dollar rates converted at LKR 333 to the dollar, our rate for November 2026 — the same rate your invoice uses.
Finance, legal and long-document work, where the answer can wait for the thinking.
Long finance, legal and research work, where a wrong answer costs more than no answer.
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.
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."}],
)Gemini models are processed on international infrastructure, outside Sri Lanka. None of them is hosted locally.
If a workload’s data has to stay in the country, Qwen 3.8 27B LK runs on our own server in Colombo.
Yes. Every Gemini model listed on this page is available from Sri Lanka through Roar AI’s API, on the same key as every other model on the platform.
Yes. Gemini usage is billed to one monthly invoice in LKR, together with any other models your team uses.
No. One Roar AI key reaches every Gemini model listed here, so there is no separate Google account or foreign card to set up.
No. Gemini models are processed outside Sri Lanka. Roar AI’s locally hosted model, Qwen 3.8 27B LK, is a separate model and is labelled as such.
One key for every Gemini model and every other model, on one monthly invoice in LKR.