About Unrestrictable.

Unrestrictable is the uncensored catalog of a multi-model API gateway run by Uplink Switch LLC, a Wyoming company. It lists only abliterated, uncensored, derestricted and roleplay builds: 147 chat models and 14 image and video models on 2026-11-01. Every chat model speaks the OpenAI wire format, so the official OpenAI SDKs and any client that takes a base URL connect with one key.

Who runs it

Uplink Switch LLC is a Wyoming limited liability company. It runs the gateway, the console where keys and top-ups live, and the API at api.unrestrictable.ai. It does not train models. Each request goes to a host that serves the build, the answer comes back, and the gateway records what was billed. The hosts are not named on this site. The models are, each with its price and its result from the daily check.

What the daily check does

Once a day every model on sale gets the same fixed test prompt and is asked for a single output token. The input token count a host reports comes from the developer’s tokenizer, so a genuine build reports the same count day after day. A swapped model, or a host that slips its own instructions into the prompt, shows up as a different count. A model put on sale after the day’s run is checked within the hour.

On 2026-11-01, 135 of 145 listed models held their count. The daily check page lists every model with its verdict: steady since a date, changed on a date, or not checked yet. It is evidence, not proof. Two builds that share a tokenizer report the same count, so the check catches a different model or an added prompt, not a swap between two tunes of one base.

How billing works

You top up a prepaid balance in the console from $10, with crypto. Each request settles against it at the input and output prices on its model’s row of the price index, counted to the token. Larger top-ups add bonus credit: 5% from $200, 10% from $500, 15% from $1,000. Each top-up also holds the prices you were paying for 30 days: inside that window a price can drop for you, never rise.

A request the host fails costs nothing. An answer the model itself refuses is free, up to $5 a day per account. When the balance can no longer cover a request, the API answers 402 and stops. No subscription is required and credit has no expiry date. Nothing is charged to a card except a top-up you make, or auto top-up, which the console’s billing page shows and switches off.

What we keep

One usage record per request: the request id, the model, token counts and the charge. Next to it, SHA-256 fingerprints of the request and the response, never the text. Prompts and completions pass through and are not written anywhere, unless you turn on replay for a key, which keeps that key’s request bodies for 7 days. The hosts that run the models receive the request and the response for the calls they serve. The privacy page has the full list.

What the gateway refuses

The gateway does not filter chat requests for content. The acceptable use policy says what you may send, and it is enforced. On every uncensored image and video model, a prompt that describes a minor is refused before it is priced or sent. An edit prompt that asks to remove clothing runs only on an image generated here, never on an uploaded photo of a real person.

Company

Uplink Switch LLC, 1309 Coffeen Ave STE 20866, Sheridan, WY 82801. Write to hello@unrestrictable.ai, or see the contact page for what to include. Keys and top-ups live in the console.