gpt-oss-120b
OpenAI’s larger open-weight model: o4-mini-class reasoning you could also run yourself.
About gpt-oss-120b
gpt-oss-120b was OpenAI’s first open-weight language model since GPT-2, released in August 2025 under Apache 2.0. OpenAI says it comes close to o4-mini on core reasoning tests and beats it on competition maths and health questions, and it scores 80.1% on GPQA Diamond. It was built to fit on a single 80GB GPU.
It reasons at low, medium or high effort and shows its full chain of thought. Its small active size makes it inexpensive to run, which makes it a sensible choice for maths, logic and structured tasks at volume.
Where it’s strong
Maths, science and logic problems.
Structured, step-by-step tasks at volume.
Agent steps that call functions.
Where to be careful
Its knowledge stops at June 2024, the oldest of the reasoning models here.
Text only.
Price in rupees
For scale: 1,000 requests of about 3,000 tokens in and 1,000 out cost $0.37 — 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.
Specs
gpt-oss-120bUsing it from Sri Lanka
gpt-oss-120b is billed in rupees, on the same monthly invoice as every other model your team uses — no foreign card, no separate OpenAI account, and one key for all of it.
Prompts sent to gpt-oss-120b are processed outside Sri Lanka. If a workload has to stay in the country, Qwen3.8-27B (Colombo) runs on our own servers in Colombo.
OpenAI tested it in 14 languages, including Hindi and Bengali, averaging 81.3% on a multilingual knowledge test. Sinhala and Tamil were not among them.
Call it
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-oss-120b",
messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)Compare gpt-oss-120b
Questions
How much does gpt-oss-120b cost in Sri Lanka?
Input is $0.0481 per 1M tokens; output is $0.221 per 1M tokens. For scale, 1,000 requests of about 3,000 tokens in and 1,000 out cost $0.37. The rate is published and does not change from one request to the next.
Can I pay for gpt-oss-120b in Sri Lankan rupees?
Yes. Usage is billed to one monthly invoice in rupees, together with every other model your team uses, and you can also pay by card. There is no separate OpenAI account to open and no foreign card needed.
Does gpt-oss-120b keep data in Sri Lanka?
No — prompts sent to gpt-oss-120b are processed outside Sri Lanka. If your data has to stay in the country, use Qwen3.8-27B (Colombo), which runs on our servers in Colombo.
Is gpt-oss-120b open source?
Its weights are open under the Apache 2.0 licence, so you could run it yourself. Through Roar AI you call it like any other model, with no servers to manage.