Gemini 4 Argon costs ₹194 per million input tokens and ₹970 per million output tokens on Roar AI, charged in Indian rupees. Google’s first Gemini 4: built for long finance, legal and research work, and quick to say when it does not know.
In Indian rupees, the currency your card is charged in, with the published US dollar rate beside each.
Example: 1,000 requests with 3,000 input and 1,000 output tokens each cost ₹1,552. Every rate is published and stays the same from one request to the next. See every model.
Rates as of 13 November 2026. Prices are our published US dollar rates converted at ₹97 to the dollar, our rate for November — the same rate your card is charged.
gemini-4-argonFor finance, legal and tax analysis across long documents, it is a strong candidate. It ranked first of 43 models on the independent Vals Index, and it hallucinated 15% of the time on Artificial Analysis’s AA-Omniscience test, the lowest of any model scoring that high on the index.
For agentic coding, compare it with Claude Opus 5.5 first. Google’s own table puts Argon behind it on Terminal-Bench 4.0, and independent reviews say it trails Anthropic’s newest models. Google’s launch pricing ends on 30 November and the rate here goes up with it, so check the price again if you decide after that date.
| Model | Input | Output | Choose it for |
|---|---|---|---|
| Gemini 4 Argon | ₹194 | ₹970 | Finance, legal and research work. |
| Claude Opus 5.5 | ₹388 | ₹1,940 | Long coding sessions and agentic coding. |
| GPT-6.1 Sol | ₹194 | ₹970 | Production agents that operate software. |
| Gemini 3.1 Pro | ₹194 | ₹1,164 | Video and audio input, and abstract reasoning. |
Prices per 1M tokens.
Argon is the first Gemini 4 model, and Google aims it at long, multi-step work in finance, law, coding and science. Independent tests mostly agree on where it is strong: it ranked first of 43 models on the Vals Index, which covers finance, legal, tax and coding tasks, and tied for third on the Artificial Analysis Intelligence Index, level with GPT-6 Astra and Claude Fable 5.1.
It is also cautious. On Artificial Analysis’s AA-Omniscience test, which penalises wrong answers but not refusals, it hallucinated 15% of the time, the lowest of any model scoring that high on the index. It is more willing than its rivals to say it does not know.
It reads text, images and PDFs in a window of about a million tokens, and you choose how hard it thinks, from low to high. Web search, reading a URL and running Python are built in: ask for one as a tool, and sources come back as citations.
We tested its reasoning effort, web search and speed tiers through our API on launch day: Gemini 4 Argon is live: pricing, benchmarks and API tests.
Roar AI provides access to Gemini 4 Argon through the Roar AI gateway, charged in Indian rupees on one bill with every other model. Requests from India go through our gateway in Bangalore. Developers can use Gemini 4 Argon alongside other supported models without a separate integration for every provider.
Use the OpenAI SDK you already have: point it at Roar AI and set the model name. Read the docs.
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-4-argon",
messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)Gemini 4 Argon is a frontier model, and requests are processed on international infrastructure, outside India. The model directory says where each model is processed.
Input is ₹194 per 1M tokens; output is ₹970 per 1M tokens. For example, 1,000 requests with 3,000 input and 1,000 output tokens each cost ₹1,552. Prices are our published US dollar rates converted at ₹97 to the dollar, our rate for November — the same rate your card is charged.
Yes. Your card is charged in Indian rupees, at our published rate for the month, on one bill with every other model you use. You do not need a separate Google account.
No. Google does not publish the weights, so it is only available through an API like this one.
Gemini 4 Argon can read up to 1.05M tokens in one request, and write an answer of up to 66K tokens.
Yes. Gemini 4 Argon reads images and PDFs directly.
Create a free account, get an API key and call Gemini 4 Argon with the OpenAI SDK, billed in Indian rupees.