OpenAI API
Use OpenAI models through one API, at a published rate, with usage on one monthly invoice alongside every other model. No separate OpenAI account needed.
OpenAI models and prices
| Model | Input / 1M | Output / 1M | Context | Best for | Processed in |
|---|---|---|---|---|---|
GPT-6 Astra OpenAI | $11.50 | $57.50 | 1.05M | Hard maths, science and agent tasks | Global |
GPT-5.6 Sol OpenAI | $4.60 | $23.00 | 1.05M | Long coding tasks | Global |
GPT-6.1 Sol OpenAI | $2.30 | $11.50 | 1.05M | Production coding agents | Global |
GPT-6 Sol OpenAI | $2.30 | $11.50 | 1.05M | Products already built on GPT-6 Sol | Global |
GPT-5.3-Codex OpenAI | $2.0125 | $16.10 | 400K | Terminal coding agents | Global |
GPT-5.6 Luna OpenAI | $0.23 | $1.38 | 1.05M | High-volume extraction | Global |
GPT-5.4 nano OpenAI | $0.23 | $1.4375 | 400K | Classification and tagging at scale | Global |
GPT-6 Luna OpenAI | $0.115 | $0.575 | 1.05M | High-volume extraction and routing | Global |
gpt-oss-20b OpenAI | $0.091 | $0.325 | 131K | Quick reasoning steps | Global |
gpt-oss-120b OpenAI | $0.0481 | $0.221 | 131K | Maths, science and logic | Global |
TTS-1 OpenAI | $17.25 characters | — | — | Real-time voice replies | Global |
Whisper large-v3-turbo OpenAI | $14.4444 audio seconds | — | — | Transcripts and captions | Global |
text-embedding-3-large OpenAI | $0.1495 | — | 8K | Multilingual search and retrieval | Global |
text-embedding-3-small OpenAI | $0.023 | — | 8K | Low-cost search and retrieval | Global |
Per million tokens, in US dollars, unless a row names another unit.
Which OpenAI model to use
The current middle tier: production coding agents, professional documents and spreadsheet work.
The flagship, for advanced maths and science and the hardest end-to-end agent tasks.
The cheapest GPT-6, for sorting, extracting and routing at volume with a million-token context.
Classifying, tagging and ranking large volumes of text.
Search and retrieval over your own documents, including languages other than English.
Transcripts and captions in 99 languages, Sinhala and Tamil among them.
Calling the OpenAI API
The Roar AI gateway speaks the OpenAI API format. Point the OpenAI SDK at Roar AI and name a OpenAI 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="gpt-6.1-sol",
messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)Where OpenAI requests are processed
OpenAI models are processed on international infrastructure. Your requests enter through the Roar AI gateway nearest you; the rest of the way, the route is the one we chose for each model, and it stays the same from call to call.
Questions
Can I use the OpenAI API through Roar AI?
Yes. Every OpenAI model listed on this page is available through Roar AI’s API, on the same key as every other model on the platform.
How is OpenAI usage billed?
At the published rate per model, on one monthly invoice together with any other models your team uses. The rate does not move with what a provider charges us.
Do I need a separate account with OpenAI?
No. One Roar AI key reaches every OpenAI model listed here, so there is no separate OpenAI account to set up.
Where are OpenAI requests processed?
OpenAI models are processed on international infrastructure. Your requests enter through the Roar AI gateway nearest you.
OpenAI and every other model,
on one key
One key for every OpenAI model and every other model, on one monthly invoice.