Call models from OpenAI, Anthropic, Google, Meta and more with one API key, and pay for all of them on one bill. A gateway in Sydney is coming soon. Pay in Australian dollars.
Calls are answered near your users, and move to a healthy route if a provider fails.
Calls go through Singapore today, the nearest gateway. Your key and code stay the same when Sydney is live.
If a provider drops, requests move to a healthy route for the same model automatically.
Transcription too, all through the same connection as your chat models.
Not every job needs your best model. Labelling thousands of rows, summarising a folder of notes, pulling fields out of invoices: your assistant can hand the work to a fast, cheap model through Roar AI and bring back the results, on the same account and the same bill.
Running a job needs an assistant that can run code, such as Claude Code, Cursor or Codex.
Your assistant sees every model on your account, with what it can do and what it costs, and picks a fast, cheap one for bulk work.
It makes a key that can only call models, with a spending cap, so a long job cannot run away with your budget.
Every model answers on the same OpenAI-compatible API, so trying another one is a one-line change.
Thinking, tools, JSON, files, search and caching. Each model’s strengths work through the same API, so switching models never means rewriting your code.
Turn a model’s thinking up or down with one setting, and read its reasoning where the model shares it.
Let a model call your functions, several at once if it needs to, in the same format on every model.
Ask for JSON that matches your schema and get it back in exactly that shape, on the models that support it.
Send a PDF to any chat model; we read it for the ones that can’t. Screenshots and photos go to the models that see images.
Let Claude or GPT look things up as it answers, with citations back to where each fact came from.
A long prompt you send again is billed at the cheaper cached rate, automatically. Set your own cache points when you want control.
Faster answers for a premium when someone is waiting, on the models that offer it. Charged only when it is served.
Send thousands of requests as one file and collect the results within 24 hours, for about half the usual price on most models.
Not every model does everything. The model pages list what each one supports.
One price per model, shown before you call it. It does not move with what a provider charges us, so the bill you expect is the bill you get.
Decide what data can leave, how much can be spent and what each key can do.
Personal data and secrets can be caught before a call reaches an outside model: redacted, blocked, or sent to a private one.
Caps per key, project or account, counted from real usage. The tightest one wins.
Scope every key, so a prototype cannot reach what production can.
See what was sent and what came back, encrypted at rest. Turn it off for your organisation if you would rather nothing was kept.
The OpenAI API calls you already use, on one key.
One address and one key that reach models from many AI companies. Instead of an account, a card and a contract with each of them, you send every request to the gateway and it passes it to the model you asked for. Roar AI also holds one route per model, so a model behaves the same way on every call.
Most LLM gateways pick who serves each request on price, per call, so the same model can accept a setting on one call and reject it on the next. Roar AI picks one route per model and holds it, with others behind it for when one fails, so a model behaves the same way every time.
Calls from Australia go through Singapore today, the nearest gateway. One in Sydney is coming soon, and your key and code stay the same when it does.
If you use the OpenAI SDK, two lines: the address and the key. Every model on Roar AI answers on the same API, and the same key also covers embeddings, images, speech and batch.
Yes. Attach a PDF to a chat request. A model that reads PDFs gets the file as it is. For the rest, Roar AI reads it first, at no charge, and pass the model the text of each page, plus an image of any scanned page when the model can see images. You pay the model’s normal rate for what it reads.
200+ from OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek and more, including a few open-source models that Roar AI runs on its own hardware.
The request moves to a healthy route for the same model, automatically. It never quietly switches you to a different model.
One account and one bill for every model, with your card charged in Australian dollars at Roar AI’s published rate for the month. Each model’s rate is published on the pricing page, and it does not move with what a provider charges Roar AI.
Using OpenRouter today? See how Roar AI compares, including when to stay.
Create a free account, get an API key and point your OpenAI SDK at Roar AI.