EN ▾
Get API key

Unfiltered AI Models: Pay-As-You-Go Pricing

Our uncensored API uses a straightforward prepaid balance so your costs scale directly with your token usage. There are no monthly fees or hidden tiers, just transparent rates for input and output tokens.

No subscription. Prepaid credit never expires.

$0.15per 1M input tokens
$0.50Output tokens / 1M
100,000token context
$0.50trial credit
300requests per minute

Top-ups from $20 to $500, any whole amount. Bonus credit: +5% from $50, +10% from $100, +15% from $200.

Cost calculator

$0.00

Worked examples

Long-context document analysis

Processing a 32,000 token document with a 2,000 token summary response costs $0.0048 for input and $0.001 for output, totaling $0.0058 per document. This workload benefits from our 100k context window without paying for unused capacity.

High-volume chat completions

A batch of 100 requests averaging 1,000 input tokens and 500 output tokens each uses 100,000 input tokens ($0.025) and 50,000 output tokens ($0.05), totaling $0.075. This demonstrates how small, frequent calls accumulate predictably.

Creative writing session

A single long-form generation using 4,000 input tokens and 8,000 output tokens costs $0.001 for input and $0.008 for output, totaling $0.009. This allows you to test abliterated model creativity at a minimal per-session cost.

Usage Rates

The uncensored llm pricing is structured around token consumption rather than subscription tiers. You pay $0.15 per million input tokens and $0.50 per million output tokens. This ratio reflects the higher computational cost of generating text compared to processing it. Input tokens include your prompt, system instructions, and any context window data sent to the model. Output tokens represent the text the model generates in response.

Our unfiltered ai models endpoint supports streaming, so you only pay for tokens actually generated. If a model stops early due to a stop sequence, you are not charged for non-existent tokens. This structure ensures you only pay for the work the GPU performs. There are no fees for API calls themselves, so high-frequency requests do not incur extra costs beyond the token usage.

Prepaid Credit & Bonuses

We operate on a pay-as-you-go model with prepaid credit. You top up your account with a minimum of $20, and your balance deducts automatically as you consume tokens. This system keeps your spending predictable and eliminates surprise bills. You can add funds by crypto (USDT on TRC20, USDC on Base), and your credits never expire.

We offer bonuses for larger top-ups to reduce your effective cost per token. Adding $50 grants a 5% bonus, while adding $100 provides a 10% bonus. These bonuses are applied to your balance immediately and can be used for both input and output tokens. This makes the uncensored api more economical for developers running consistent workloads. You can check your remaining balance and usage history directly from your dashboard at any time.

Trial Credit

New accounts receive $0.50 in trial credit valid for seven days. This allows you to test the unfiltered chat api without entering payment details. Claim this credit with one click on your API key page. No credit card is required to start, making it easy to verify model quality and latency before committing. The trial credit covers both input and output tokens, so you can run realistic workloads to evaluate performance.

Once your trial credit is exhausted or the seven days pass, you must add funds to continue using the service. You can regenerate your API key at any time without affecting your balance. This trial is limited to one per person, ensuring fair access for new developers exploring our uncensored llm capabilities. It is an ideal way to integrate the API into your development workflow before scaling up with paid credits.

What your credit buys

Same price for every feature — function calling and JSON mode cost nothing extra.

FeatureSupport
Completion lengthprompt + completion fit within 100,000 tokens; max_tokens optional, no separate output cap
Max context100,000 tokens, input and output combined
JSON modeJSON object mode via response_format json_object
Tools / tool callsSupported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages
Parallel requestsup to 8 in parallel per key
Rate limit300/min per key
Free trial$0.50 for 7 days, no card · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up
Token pricesinput $0.15 / 1M tokens, output $0.50 / 1M tokens
Bonus credit+5% from $50, +10% from $100, +15% from $200
Top-upcrypto: USDT on TRON or USDC on Base, $20–$500, any whole sum
Credit expirypaid credit never expires, no subscription

All limits and error codes are listed in the docs.

Questions and answers

Can my bill exceed my prepaid balance?

No, your account stops processing requests once your balance reaches zero. Since we use a prepaid model, your usage can never exceed what you have loaded, ensuring predictable spending.

Do credits expire if I don't use them?

Paid credits never expire. You can top up today and use the tokens months later. The only time-limited credit is the $0.50 trial, which expires after seven days.

How are tokens counted in the uncensored api?

Tokens are counted based on the text sent in your request (input) and the text generated by the model (output). We use standard tokenization, so you can estimate costs using your preferred SDK's tokenizer.

Is there a monthly fee for this uncensored ai model service?

No, there are no monthly fees or subscriptions. You only pay for the tokens you consume. If you do not use the API, you do not pay anything.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.