GPT-6.1 Sol costs LKR 666 per million input tokens and LKR 3,330 per million output tokens on Roar AI, billed in Sri Lankan rupees on one invoice. OpenAI’s current middle tier, close to Astra on agent work at a much lower price.
Prices are shown in LKR to make model costs easier to estimate and manage for Sri Lankan teams, with the published US dollar rate beside each.
Above 272,000 input tokens, the whole request is billed at the long-request rates.
Example: 1,000 requests with 3,000 input and 1,000 output tokens each cost LKR 5,328. Every rate is published. See every model.
Rates as of 20 November 2026. 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.
gpt-6.1-solFor production coding and agents, yes. OpenAI says it matches GPT-6 Astra on DeepSWE at about a fifth of the cost, and lands within about two points of it on OSWorld at roughly a seventh of the cost per task.
Those are OpenAI’s own numbers and independent testing is still thin, so compare it on your own work with Claude Sonnet 5.5, its like-for-like rival on price. Move up to Astra only for the hardest science and maths.
| Model | Input | Output | Choose it for |
|---|---|---|---|
| GPT-6.1 Sol | LKR 666 | LKR 3,330 | Production coding agents. |
| Claude Sonnet 5.5 | LKR 666 | LKR 3,330 | Faster everyday work. |
| Claude Opus 5.5 | LKR 1,332 | LKR 6,660 | Messy, judgement-heavy work. |
| GPT-6 Astra | LKR 3,330 | LKR 16,650 | The hardest science and maths. |
Prices per 1M tokens.
GPT-6.1 Sol came out at OpenAI’s DevDay on 29 September 2026, a week after GPT-6 Sol and at the same price. OpenAI says it matches GPT-6 Astra on the DeepSWE coding test at about a fifth of the cost, and lands within about two points of Astra on OSWorld, the computer-use test, at roughly a seventh of the cost per task.
It is the GPT to pick for production agents that need to be both good and affordable: coding, operating software, building documents and spreadsheets. It always reasons a little, since the lowest setting is low, and OpenAI says it makes a factual error in about a third fewer answers than GPT-6 Sol at that setting.
Roar AI provides access to GPT-6.1 Sol through the Roar AI gateway, with usage billed in LKR and no foreign card needed. Developers can use GPT-6.1 Sol alongside other supported models without maintaining 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="gpt-6.1-sol",
messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)GPT-6.1 Sol is a frontier model, and requests are processed on international infrastructure, outside Sri Lanka.
Roar AI’s locally hosted model is separate and is labelled as such: if a workload has to stay in the country, Qwen 3.8 27B LK runs on our own server in Colombo.
See every OpenAI model and its price in rupees. Explore all AI models available in Sri Lanka
Input is LKR 666 per 1M tokens; output is LKR 3,330 per 1M tokens. For example, 1,000 requests with 3,000 input and 1,000 output tokens each cost LKR 5,328. 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.
Yes. GPT-6.1 Sol usage is billed in LKR on one monthly invoice with every other model you use, so there is no foreign card or separate OpenAI account to set up.
No. OpenAI does not publish the weights, so it is only available through an API like this one.
GPT-6.1 Sol can read up to 1.05M tokens in one request, and write an answer of up to 128K tokens.
It reads images directly. You can still send it a PDF: Roar AI turns each page into text first, at no extra charge.
Create a free account, get an API key and call GPT-6.1 Sol with the OpenAI SDK, billed in Sri Lankan rupees.