JETINFER

Terms of service

Effective 2026-08-31 · applies to the inference API at api.jetinfer.com

Prepaid credit, sold by us. You pay only for tokens we actually serve, we never train on your data, and we don't promise an uptime SLA yet. Either side can walk away at any time.

Who we are

JetInfer is operated by Quantive Betéti Társaság ("Quantive Bt."). “We” and “us” mean Quantive Bt.; “you” means the person or company using the API.

Registered seat1171 Budapest, Erzsébet körút 55., Hungary
Company registerCg. 01-06-798410, Fővárosi Törvényszék Cégbírósága
Tax number32660706-2-42
EU VAT numberHU32660706
EmailFeedback: hello@jetinfer.com

What we provide

An OpenAI-compatible inference API serving Qwen3.8-27B, quantized to int4 (W4A16). The quantization is disclosed on the landing page and in the /v1/models response, because it affects output quality and you should know what you are buying.

We may change models, rates or capacity. A rate change is published in /v1/models before it takes effect, and withdrawing a model removes it from that response. You're never charged a rate that wasn't published before your request.

What we charge

Per token, at the rates in /v1/models. That response is generated from the same table that bills you, so it is the authoritative price. This page doesn't repeat it: rates move, and a copy here would eventually contradict what you are charged. What bills how is on the specifications page and doesn't change with the rate.

Credit is prepaid. You buy it up front, requests draw it down, and nothing renews. When it runs out we refuse requests with a 402 until you top up. Card payments are handled by Stripe and card details never reach us.

Rates are before tax. VAT is added at checkout at the rate for where you are. If you're a business in the EU outside Hungary, enter your VAT number and the reverse charge applies, so we add nothing. Whatever tax you pay is on top of the credit you buy, never taken out of it: the credit you pay for is the credit you get. Invoices are in your billing portal.

You are never billed for a request we failed to serve. A request that returns an error, or one we can't account for token usage on, is not charged.

What we do not promise

These are the limits of what we owe you:

The service is provided “as is”, without warranties of any kind so far as the law allows. Our total liability for any claim is limited to the amount you paid us in the three months before the claim arose.

Acceptable use

Do not use the API to:

We may refuse or suspend traffic doing any of the above, and where it's safe to we'll tell you why first. If we suspend you for abuse we may withhold unspent credit; in every other case it is refunded.

Your data

We never store prompts or outputs, and we never train on your data. The detail is in our privacy and data retention policy, which forms part of these terms.

You keep every right in what you send and in what the model returns to you. We claim no licence over either.

Ending it

You can stop sending us traffic whenever you like, and nothing further is owed. We can stop serving with notice, or immediately where the law requires it or in response to abuse. If we end it, we refund whatever credit you haven't spent. You're charged for served tokens only either way.

Changes and governing law

When these terms change we update this page and the effective date above. Material changes are published here before they take effect. These terms are governed by Hungarian law and the courts of Hungary have jurisdiction, without affecting consumer protections you hold where you live.

Contact

Questions about these terms, about billing, or about anything else: hello@jetinfer.com.