Long article summarization
A request with 5,000 input tokens and 1,000 output tokens costs: (5,000 / 1,000,000 × $0.25) + (1,000 / 1,000,000 × $1.00) = $0.00125 + $0.001 = $0.00225.
OpenAI-compatible API with zero content filters for adult use
https://api.llmsemcensura.com/v1uncensored
Our uncensored llm API uses a direct pay-as-you-go model, with no monthly fees or hidden costs. You top up credits and pay only for the tokens you actually process, keeping full control of your budget.
No subscription. Prepaid credit never expires.
A request with 5,000 input tokens and 1,000 output tokens costs: (5,000 / 1,000,000 × $0.25) + (1,000 / 1,000,000 × $1.00) = $0.00125 + $0.001 = $0.00225.
A request with 10,000 input tokens and 2,000 output tokens results in: (10,000 / 1,000,000 × $0.25) + (2,000 / 1,000,000 × $1.00) = $0.0025 + $0.002 = $0.0045.
A request with 30,000 input tokens and 5,000 output tokens costs: (30,000 / 1,000,000 × $0.25) + (5,000 / 1,000,000 × $1.00) = $0.0075 + $0.005 = $0.0125.
uncensored model. There are no platform fees or fixed monthly costs. You pay exactly for what you use, which makes the uncensored AI API ideal for projects with variable NLP processing volume.
Unlike many providers that expire your balances, our prepaid credits never expire. You can buy a larger amount of credit and use it over time, without pressure to spend quickly. This allows you to take advantage of low-demand periods or run large-scale tests without losing money. The remaining balance stays available for your next requests, ensuring your investment is always ready when you need it.
Same price for every feature — function calling and JSON mode cost nothing extra.
| Parameter | Details |
|---|---|
| Context window | 64,000 tokens, input and output combined |
| Tools / tool calls | Yes — tools, tool_choice; replies carry tool_calls, also when streaming; send results back as role: tool |
| JSON mode | JSON object mode via response_format json_object |
| Max output | prompt + completion fit within 64,000 tokens; max_tokens optional, no separate output cap |
| Concurrency | up to 8 in parallel per key |
| Requests per minute | 300/min per key |
| Price | $0.25 per 1M input tokens · $1.00 per 1M output tokens |
| Trial credit | $0.50 for 7 days, no card · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up |
| Bonus credit | +5% from $50, +10% from $100 |
| Top-up | USDT (TRC20) or USDC (Base), any whole amount from $10 to $500 |
| Subscription | no monthly fee; paid credit does not expire |
No. Upon creating your account, you receive $0.50 in free trial credit to test the API. No credit card or phone number is required to access this initial credit.
Each request can contain up to 100,000 tokens combining input and output. The request body cannot exceed 8 MB. These limits ensure the model processes the necessary context without overloading the server.
There is no monthly subscription to cancel. Your credit balance remains in the account until used or until you decide to stop using the service. There are no cancellation fees or penalties for inactivity.
Requests will fail if there are not enough credits in the account. Since payment is prepaid, your usage will never exceed the amount you topped up, ensuring total cost predictability.
Create an account, copy the key and change the base URL. That's all the setup.
https://api.llmsemcensura.com/v1