NoLimitsAISTARTER
$9.99 / week
Weekly subscription
Ask about StarterLOW COST. MORE CHOICE. YOUR MODEL.
More AI.
Less overhead.
Explore low-cost models and uncensored variants where available, with transparent token rates.
Choose the model in your compatible client.
— models— model families
Lower listed rates.
See token costs up front, model by model.
Cache smarter. Spend less.
Compare standard and cached-input rates.
Built around your stack.
Copy model IDs into your integration.
SUBSCRIPTIONS
Choose a plan.
Subscription price points, billed in USD. Online checkout is being connected.
PRO
$19.99 / month
Monthly subscription
Ask about ProMAX 5×
$99.99 / month
Monthly subscription
Ask about Max 5×MAX 20×
$199.99 / month
Monthly subscription
Ask about Max 20×Plans are not purchasable yet. Payment processing and subscription access are not enabled. Price points copied from Unjailed AI pricing.
01 / EXPLORE THE CATALOG
Choose your edge.
Low-cost options and uncensored variants where available. Rates, in the open.
RATE SNAPSHOTLoading current catalog details…
Loading model rates… If they do not appear, refresh or check that JavaScript is enabled.
No models found
Try a different name or clear your filters.
02 / CHECK THE BENCHMARK
Our rates vs official API prices.
Matched models are compared with provider-published token rates.
HOW TO READ THISOur catalog uses one standard rate for both input and output. The comparison uses an example 3:1 input-to-output mix (75% input, 25% output), plus a separate cached-input comparison. Results vary with your workload and provider pricing tiers.
| Model / provider | Our standard rate | Official input / output | 3:1 estimate vs official | Cached rate comparison | Source |
|---|
Uncensored and abliterated entries use an official base-model price as a reference where a direct official equivalent is not published. This is a price benchmark, not a claim that the models are identical. It compares public API list prices and does not verify wholesale costs or profit margin. Provider list prices may change; checked November 8, 2026.
03 / RUN THE NUMBERS
Your ambition.
Your budget.
Big workloads shouldn't mean blind guesses. Dial in your usage and see the math.
Cached tokens replace standard input. Never double-counted.
WORKLOAD ESTIMATORUSD
Estimated workload cost
Reference estimate only. Excludes taxes, payment fees and any service-specific charges.
04 / CLIENT SETUP
Choose your model.
Keep your workflow.
Ask support for a private all-model config and install guide.
A few useful answers.
What does “per million tokens” mean?
A token is a unit of text processed by a model. Multiply the token count by the rate and divide by 1,000,000. The estimator separates standard and cached input usage.
Are these checkout prices?
These are reference rates from the dated catalog with a 30% markup. Checkout and live model routing are not connected yet.
Can I buy credits here?
Not yet. The payment provider and production service still need to be connected before real payments can be accepted.
Which clients work?
OpenAI-compatible clients that can use non-streaming Chat Completions can use the connection settings. This gateway does not yet support streaming or the Responses API, and client tool compatibility is unverified.