Its instructions, one model and the live data it may use, kept together. Agents aren't open yet: when they open, you'll run one from your console or put it on a page your customers can use, paid from the same wallet. Your own agent tool works with our API today.
Bring your own works now. The other two open with Agents, and there's no date yet.
When Agents open, you'll save an agent — a name, instructions, one model and the live data it may use — and run it from your console. You'll describe the job in a sentence, or start from one of the five templates below.
Point OpenClaw, or any agent tool that takes a base URL and a key, at our API. We don't run your agent: we serve the model it calls, from 25+ open models, paid per token from the same wallet.
How to set it up →Publishing comes when Agents open. You'll put an agent on its own page at yourname.oraicle.app, or on your own site with one line of HTML, and it will stop at the daily cap you set.
When Agents open, the console will offer these five as starting points. You'll pick one, change what you like and save it.
Answer a question with facts and where each one came from.
A dated summary of what happened on the topics you name.
Draft a reply to a customer message, in your tone, for you to send.
Prices and moves for the tickers and coins you name.
Turn a company or person name into a short profile with sources.
Each run will be paid from the same wallet, at the same per-token and per-lookup prices as the chat, with no subscription for agents. A published page will be able to use your account's one free site, or go on a hosting plan.
The tokens it reads and writes, at the model's price per million, plus each live-data lookup it makes, at that source's price. A research brief — about 3,000 tokens in and 800 out on GPT-OSS 120B, with one web and one news lookup — would cost about $0.007 at the listed prices.
It won't remember earlier runs, and you won't be able to reach it in Telegram at first; both are planned. It will never run code or install add-ons, and it will use only the live data you switch on for it.
One thing: ask that one agent a question. The key will sit in the page's source, where anyone can read it, so it won't be able to change the agent, pick another model, see your balance or reach anything else in your account. The daily cap is what will protect your wallet, and you'll be able to rotate the key or unpublish the page from the console.
The page will say it has reached today's limit and answer nothing more until the next day (UTC), and a question refused at the cap will cost nothing. The cap will be $1 a day unless you change it, $20 at most, and publishing will need a balance at least as large as the cap.
Yes, today. Point OpenClaw, or any agent tool that takes a base URL and a key, at our API with a key from the console. We don't run your agent; we serve the model it calls, and each call is paid per token from your wallet. Use your own agent with Oraicle →
We don't have a date yet, and we won't announce one until it's certain. Meanwhile, your own agent tool works with our API, and the chat with live data does much of the same work — pick a model, switch on the live data you need, and ask.
It creates a free account (with $0.25 of credit to try the models today) and turns on a switch in your console's Agents tab. You get one email when Agents open — nothing else.
No. You'll describe the job in plain words or start from a template, and see what it set up before anything is saved. Bringing your own agent tool means editing its settings file; the docs page shows every line.
The same 25+ open models as the chat — DeepSeek, Qwen, Kimi, GLM, Llama, gpt-oss and more. The console will offer live data only on the models that can use it.