Roar AI
Get started
All models
OpenAI · Chat

GPT-6 Astra API in India

OpenAI’s flagship, for the hardest maths, science and long agent work. Priced in Indian rupees for teams in India, on the same key as every other model.

Input₹1,009.40per 1M tokens
Output₹5,047.00per 1M tokens
BillingOne bill, in INRwith every other model

GPT-6 Astra API pricing in India

Input₹1,009.40 per 1M tokens · $10.30
Output₹5,047.00 per 1M tokens · $51.50
Cached input₹100.94 per 1M tokens · $1.03
Cache write₹1,261.75 per 1M tokens · $12.875
Batch input₹504.70 per 1M tokens · $5.15
Batch output₹2,523.50 per 1M tokens · $25.75

In Indian rupees, the currency your card is charged in, with the published US dollar rate beside each.

For scale: 1,000 requests of about 3,000 tokens in and 1,000 out cost ₹8,075.20 — a long prompt and a page of answer each. Every rate is published and stays the same from one request to the next. See every model.

Prices are our published US dollar rates converted at ₹98.00 to the dollar, our rate for October — the same rate your card is charged.

About GPT-6 Astra

Astra is the top of OpenAI’s GPT-6 family and the model OpenAI calls its most capable. Its launch numbers are strongest in maths and science — 96.0% on GPQA Diamond and 97.6% on FrontierMath Tier 4 — and in operating software, with 92.7% on ScreenSpot-Pro. OpenAI says it gets there with roughly 70% fewer tokens than GPT-5.6 Sol on the same tasks.

It is also the first model OpenAI has rated “Critical” for cybersecurity, and it went to defensive-security programmes first. It always reasons, from low to max effort. A week after it launched, GPT-6.1 Sol came within a point or two of it on most agent tests at a fraction of the price, so try Sol before you pay for Astra.

What is GPT-6 Astra good for?

  • Advanced maths and science problems.
  • The hardest end-to-end agent tasks.
  • Operating software through its interface — reading screens, clicking, typing.
  • Problems where a cheaper model’s answer is not good enough.

Where to be careful

  • Slower to answer than the Sol and Luna tiers, and it cannot be told not to reason.
  • On Humanity’s Last Exam it trails Claude Fable 5.1, 57.2% against 65.0%.
  • GPT-6.1 Sol matches it on many agent tasks at a much lower rate. Test both.

Specs

Made byOpenAI
ReleasedSeptember 2026
TypeChat
Context window1.05M tokens
Longest answer128K tokens
ReadsText, Images
Thinks before answeringAlways on
WeightsClosed
Processed inGlobal
Model idgpt-6-astra

Using GPT-6 Astra from India

Roar AI provides access to GPT-6 Astra 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 GPT-6 Astra alongside other supported models without a separate integration for every provider.

Use the OpenAI SDK you already have — point it at Roar AI and name the model. 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="gpt-6-astra",
    messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)

Where is GPT-6 Astra processed?

GPT-6 Astra is a frontier model, and requests are processed on international infrastructure, outside India. The model directory says where each model is processed.

Questions

How much does GPT-6 Astra cost in India?

Input is ₹1,009.40 per 1M tokens; output is ₹5,047.00 per 1M tokens. For scale, 1,000 requests of about 3,000 tokens in and 1,000 out cost ₹8,075.20. Prices are our published US dollar rates converted at ₹98.00 to the dollar, our rate for October — the same rate your card is charged. The rate is published and does not change from one request to the next.

Is GPT-6 Astra open source?

No. OpenAI does not publish the weights, so it is only available through an API like this one.

Try GPT-6 Astra
on one key

Sign up, get a key and call it with the SDK you already use. Pay in your local currency, on one bill.