Cheap, uncensored LLM API
Uncensored AI Pricing & Billing
Pay only for the tokens you actually consume with our uncensored AI pricing. We skip subscriptions and hidden fees so your budget stays predictable from the first request to the last.
- $0.15
- per 1M input tokens
- $0.50
- Output tokens / 1M
- 100,000
- token context
- $0.50
- trial credit
- 300
- requests per minute
Pricing estimator
No subscription. Prepaid credit does not expire.
Usage examples
A developer testing creative writing prompts with low complexity.
Sending 50,000 input tokens and 2,000 output tokens costs $0.0075 for input plus $0.001 for output, totaling $0.0085 per request. This low-cost model lets you iterate rapidly without worrying about per-request overhead.
Processing a large context window for content summarization.
Using 80,000 input tokens and 4,000 output tokens results in $0.012 input cost and $0.002 output cost, totaling $0.014. You get full access to the 100k context window without paying for unused capacity.
Running a batch of function calls with short responses.
Submitting 10,000 input tokens and 500 output tokens costs $0.0015 for input and $0.00025 for output, totaling $0.00175. Streaming responses ensure you only pay for the actual tokens generated by the uncensored model.
Transparent Per-Token Rates
Our uncensored API charges exactly $0.15 per million input tokens and $0.50 per million output tokens. You never pay for idle time or reserved capacity because we bill strictly on usage. This structure ensures that complex reasoning or longer outputs scale linearly with your actual consumption. Errors and refusals incur no charge, so you only pay for successful completions. The lack of a subscription fee means your costs drop to zero when you stop using the service. This approach eliminates the surprise egress fees common in larger platforms.
Prepaid Credit & Expiry
You top up your account with prepaid credit that never expires. Your balance decreases only when the model processes tokens, giving you precise control over your spending. You can monitor your remaining credits in real-time through the dashboard. If you pause development for a month, your funds remain available for when you return. This system prevents the dreaded auto-renewal trap where you pay for a month you did not use. Your credit is yours until you decide to spend it.
Why Prepaid Keeps Spend Predictable
Prepaid billing locks in your maximum possible cost because you cannot spend more than your deposited amount. This is critical when running multiple keys or automating high-volume tasks. With our uncensored AI pricing, you know exactly how many requests your budget covers before you start. This transparency allows developers to allocate specific dollar amounts to different projects without tracking complex usage tiers. It is simple accounting for complex AI workloads.
Common questions
View API referenceHow does the prepaid credit work for uncensored AI usage?
You deposit funds to create a balance that deducts only when tokens are consumed. The system charges $0.15 per million input tokens and $0.50 per million output tokens. Your balance updates in real-time as requests complete, so you always know your remaining funds.
Does my prepaid credit expire after a certain period?
No, your prepaid credit never expires regardless of how long you wait to use it. You can deposit funds and use them weeks or months later without losing any value. This flexibility is ideal for developers who work on projects intermittently or need to secure a specific budget for future sprints.
What happens if I accidentally spend too much from my balance?
Requests stop once your balance reaches zero, so you cannot go into debt. You simply top up your account to resume service. There are no overage fees or surprise charges on a separate payment method because the prepaid system caps your spending at your deposited amount.
Is there a minimum amount I must spend to use the API?
The minimum top-up amount is $20 when using crypto payments. You can deposit any whole amount between $20 and $500 per transaction. This low entry point allows developers to test the uncensored model with minimal upfront cost before committing to larger budgets for production work.
Get your API key now
Register, grab the key, and swap the base URL. That is all the configuration required.
