An OpenAI-compatible LLM API. Point any OpenAI SDK at our endpoint, change the base URL and key, and it works. You get AEON — our own 27B model on our own GPU fleet — private by default. See our Acceptable Use Policy for what's allowed.

No. Prompts and completions are never written to disk — we process them in real time and keep nothing. We only count tokens, for billing, and we don't train on your data. Details in our Privacy Policy.

Today: aeon-27b — our own 27B model (AEON). It's OpenAI-compatible, so any OpenAI SDK works. More models are coming under the same API and account — see Models.

Pick a plan on Pricing, pay, and copy your key. Then point any OpenAI SDK at https://plusapi.ai/v1 with your key. Full walkthrough in the docs. No sales call, no waitlist.

Crypto (Bitcoin, Monero, USDT) or card. Payment is prepaid — a monthly plan. No card is stored for crypto, and there are no chargebacks or surprise account freezes.

Crypto payments and used credits are non-refundable, in line with industry practice — see our Refund & Payments policy. Not sure which plan fits? Ask us first.

We store only a hash of your key, so a lost key can't be recovered — that's the privacy trade-off. Keep it safe; if you lose it, contact us and we'll issue a new one.

Yes — a drop-in replacement. Change base_url to https://plusapi.ai/v1 and your key, and the same /v1/chat/completions calls (including streaming) work unchanged.

Each plan sets max parallel requests, requests-per-minute, context window, and a generous monthly token allowance (fair use). Full table in the docs. Need more? Move up a plan or talk to us about Dedicated.

Yes — the Dedicated plan gives you a private multi-GPU box with guaranteed concurrency, custom context, and an uptime SLA. Talk to us about volume.