Help
About
onomeo offers an OpenAI-compatible API and browser chat. Paid models use your balance; eligible rewards cover selected answers in browser chat. Available models and prices are listed in the current catalogue.
What it is
A single API endpoint that accepts the same request shape as the OpenAI chat API. Point an existing client at it, supply the key issued to your account, and the requests go through unchanged. There is also a browser chat page for people who do not want to write code.
How billing works
Paid text models are charged by usage from your dollar balance. Image generation uses the price shown for the selected model. Earned rewards can cover eligible answers in browser chat; they do not cover image generation or API calls. Models explicitly listed as free use separate call limits. Check the current models and prices before sending. Your balance never expires and does not renew automatically; it cannot be transferred, sold or withdrawn as cash. Details are in the terms.
No data is resold — what we do and do not store is set out in the privacy policy.
Why the balance is tied to an account
Signing in with a verified email address or a Google, GitHub or Discord account is required before the service can be used. A balance stored only in a browser would disappear the moment someone clears their site data; tied to an account, the balance, conversations and earned rewards stay the same on a new device or after the browser is cleared.
Open beta
onomeo is in open beta. Features may change, and not every model or feature is guaranteed to work at all times. Feedback is welcome. Before you build anything important on top of it, see the terms for what is and is not guaranteed.
Current limits
- Any models marked as free in the current catalogue have separate call limits. The billing rules show the limits the site currently publishes.
- Image generation is subject to the model and account limits shown before sending.
- Paid models use your balance. Eligible invitation trials and earned rewards can cover selected answers in browser chat; availability, remaining answers and daily limits are shown in your account and the model picker.
- Every account is also limited in calls per minute, on every model.
- Available models are listed on the models page and can change.
Getting in touch
Questions, problems, and abuse reports all go to the address on the contact page. The contact page says what to include so a reply is useful.
Last updated
FAQ
How is usage charged?
Chat is charged by usage from your dollar balance. Image generation is charged per image at the price shown for the selected model, only after the image is generated and saved; failed images are not charged. Current models and prices are on the Pricing page. A first original work that passes review earns free answers on selected models in browser chat; these rewards do not cover image generation or API calls. Calls using your own NovelAI key are billed by NovelAI under your plan.
What are the limits on free models?
Free models are not charged; they are limited by number of calls: 30 calls per account every 5 hours and 60 per network. When the calls shared by the whole site run out, free models pause for everyone for a while. A longer message counts as several calls. Its length is counted over everything sent with it: the message together with the conversation so far and any attached file text. Each Chinese character counts 1 and every 4 other characters (letters, digits, spaces, punctuation) count 1, and each 8,000 counted, or part of it, is one call. So 32,000 Chinese characters count as 4 calls, while the same length of English text or code counts as about 1; once a conversation has reached 16,000 counted, even a short new message counts as at least 3. A message that, together with the conversation so far, is longer than 32,000 counted is not sent to free models; shorten the conversation or start a new one. If fewer calls are left than a message needs, it is not sent, and the page says how many calls it needs, how many are left in this window and when more come back. Claude, GPT and other big models are charged by usage to your balance and do not count toward these calls.
Why do I have to sign in?
Signing in keeps your balance, conversations, images and earned rewards on the same account across devices. Usage and security limits are also counted per account. Signing in is free; use one of the available sign-in methods or a code sent to your email.
What happens if I lose my key?
Nothing is lost. Sign in again and the My account page issues a new key on the same account, with the same balance. If you think a key has leaked, revoke it from the My account page — the balance is unaffected.
What is the balance?
Each payment adds to your balance the amount the top-up page states, shown in dollars. Claude, GPT and other big models and the DeepSeek coding line are charged to it by usage. Free models do not touch the balance; they are limited by calls. The balance never expires and nothing renews automatically; top up again whenever it runs out.
Can I create several keys?
Yes, up to 10 per account — useful for separating projects. All keys on an account draw from the same balance and share the account’s call limits, so more keys do not mean more calls. Opening extra accounts to get around those limits is not allowed, and the number of new accounts per network is capped each day.
Are my prompts stored?
On the chat page, yes: conversations are saved to your account so you can return to them, up to 50, and you can delete any or all of them on the chat page. For requests sent directly to the API, an excerpt of each request and reply is kept (the latest 100 per account, for at most 30 days), and the time, the model chosen and the amount used are recorded, for billing and for counting calls. The operator can read chats and API call content in the administration area, to understand how the site is used. Either way, messages are forwarded to a third-party model provider, and some providers, particularly on free tiers, may retain what they receive or use it to improve their services. We do not use your conversations to train models. Avoid sending sensitive personal information. Details are in the privacy policy.
Can I use this in production?
Not advisable. This is a public beta with no uptime promise and no support commitment. It is built for trying things out, prototyping, and side projects. If something depends on being available at 3am, buy an API key from a provider who will answer the phone.
Which models are available?
The current list is on the models page, and the My account page shows what your key can call right now. The list can change: models get added, and a model can disappear when the upstream provider retires it.
Can I send images?
Yes, to the models marked with the image sign in the model lists. On the chat page, add up to 4 images to a message with the image button, or paste or drop them into the box. Images read by text models are included in input tokens, with no additional per-image fee. Any model marked as free has no image charge. Images are passed to the model provider for the answer and are never stored: after a reload, the conversation shows that a message had images, not the images themselves. Through the API, see the images section of the docs.
Can I upload a file?
Yes. On the chat page, use the button beside the message box or drop the file into it: PDF, TXT, Markdown, CSV, JSON and common code files, up to 4 per message and 20 MB each. The page reads the text out of the file in your browser and sends that text with your question (up to 40,000 characters), so any model can take it; it counts toward the length of the message: on big models it is charged like the rest of the message, and the estimate beside Send includes it; on models marked as free it is not charged, and a long message counts as several calls. The text stays with the conversation, so you can keep asking about the file after a reload. A scanned PDF with no text layer cannot be read; Word documents are not taken yet.
My answer came back empty. Why?
Almost always a max_tokens value set too low. These models produce reasoning before the visible answer, and if the budget runs out during that stage the visible part never gets written. Raise it and try again.
My balance ran out. Now what?
Paid models use your balance. Models marked as free remain available within their call limits. Eligible invitation trials and earned rewards can cover selected browser-chat answers; check the model picker for remaining answers. Starting a new conversation may lower the charge but does not make a paid request free. To continue with paid usage, top up on the Pricing page.
How do I top up?
Open the Pricing page and select Top up; you do not need to sign in first. The smallest top-up is $5. Each payment adds to your balance the amount the top-up page states, shown in dollars. It pays for the DeepSeek coding line, which is not limited by the free-model call counts, and for Claude, GPT and other big models, all charged by usage; free models do not touch the balance. The balance never expires and nothing renews automatically; top up again whenever it runs out. For 35 days after a payment, free models allow 90 calls every 5 hours. Answers returned through the API to accounts without a balance end with the line "— via onomeo.com". Accounts with a balance do not get it. Tool-call answers, structured-output answers and answers that consist of a single JSON object or array are never changed. If you pay with an email other than the one you sign in with here, a claim code is sent to that email; enter it on the My account page. Claude, GPT and other big models are open to accounts that have topped up; an account that has not can try them free 3 times in the chat page.
Can I give my balance to someone else?
No. The balance cannot be transferred to another account or withdrawn as cash. Sharing a key so several people can spend one balance is also not allowed: a key seen in use from several places at once gets disabled.
Contact
One address for everything
Loading the address
Expect a reply within a few days rather than within hours. Including the right details in the first message usually saves a round trip.
Something is broken
Include the time it happened, the model you called, and the error message exactly as it came back. If the request failed, the HTTP status code is the single most useful thing you can send. Never include your key — it is not needed to investigate, and anyone who sees it can spend your balance. You can also send it from the feedback page, no sign-in needed.
Account and balance
Say which email address, or which Google, GitHub or Discord account, the balance belongs to, and describe what you expected to happen. Common cases: a top-up did not arrive (include the email address used for the payment), a key stopped working after signing in somewhere else, or you want every key on the account revoked because one of them leaked.
Reporting abuse
If you have found a way around the call limits, a way to use paid models without paying, or a key being resold, please say so. Abuse can disrupt the service for everyone, so these reports are read first. Describe what you observed; a reproduction is welcome but not required.
Security
For anything that looks like a vulnerability, write to the same address with "security" in the subject line. Please give us a chance to fix it before publishing it anywhere.
Partnerships
Advertising network representatives, and anyone wanting to discuss placements or integrations, can use the same address. Publisher or app identifiers, if you have them, help us find the right context quickly.
What we cannot do
- Raise a usage limit or add to a balance on request. The limits exist so the service stays affordable enough to keep running.
- Recover a balance that was never attached to an account. Signing in is what makes a balance recoverable.
- Promise uptime or a response time. This is a public beta, as set out in the terms.
Feedback
During the open beta, every piece of feedback is read. A problem, a feature you want, anything that gets in the way: send it here, no sign-in needed.