Uncensored LLM API Pricing and Top-Up

Per-Token Pricing Model

Our pricing model charges strictly for the tokens you process, ensuring you only pay for actual inference work. Input tokens cost $0.15 per million, while output tokens are priced at $0.50 per million. This structure allows agencies to scale their usage without worrying about tiered feature locks or base subscription costs. Errors and refusals incur no charge, so you never pay for failed requests. The formula is straightforward: cost equals input tokens divided by one million times zero point one five, plus output tokens divided by one million times zero point five. This direct billing method keeps your infrastructure expenses transparent and easy to forecast. You can monitor your exact spend in real-time as your tokens are consumed. POST /v1/chat/completions requests are billed immediately upon completion. No monthly fees apply, so your costs scale directly with your demand. This approach is ideal for developers who want precise control over their API budget without complex billing surprises.

Crypto Top-Up and Bonuses

You can top up your prepaid balance using USDT on TRC20 or USDC on Base networks. We accept whole amounts ranging from $20 to $500 per transaction. We offer bonus credits to reward larger deposits. A top-up of $50 or more receives a 5% bonus. Deposits of $100 or more earn a 10% bonus. If you deposit $200 or more, you get a 15% bonus on your credit. These bonuses are applied instantly to your account balance. Your prepaid credit never expires, so you can top up whenever you need more capacity. This system ensures you always have funds available for your inference work without monthly renewals. The simplicity of crypto payments allows for fast global transactions. You can manage your account balance directly through our dashboard. No hidden fees are charged for the top-up process itself.

Free Trial and Refunds

New accounts receive $0.50 of trial credit to test our uncensored API immediately. You can generate your API key and start sending requests right away. Your prepaid credit does not expire, so you can use it whenever you are ready. If you make a mistake, such as a double charge, we will fix it through our Support page. However, the prepaid credit itself is not refunded once used. The trial credit is one per person and is non-transferable. This allows you to verify our latency and response quality before committing funds. You can see your token usage and remaining balance in real-time. Errors are free, so your trial balance is only consumed by successful completions. This low-risk entry point helps developers evaluate our infrastructure. You can switch between our API and other services without losing your prepaid balance. The trial gives you a clear view of our pricing structure.

Rate Limits and Quotas

Our rate limits ensure stable performance for all users sharing the dedicated infrastructure. You are allowed 300 requests per minute per API key. You can also have up to 8 concurrent requests at the same time. Each request body must not exceed 8 MB. We provide one active key per account, and generating a new key replaces the old one. These limits are designed for high-volume workflows without throttling your throughput. Our uncensored model runs on our own servers, offering consistent latency. You can stream responses via SSE to handle long outputs efficiently. The context window supports 100,000 tokens for both prompt and completion. Max output is capped at 16,000 tokens per request. If you do not set max_tokens, the default is 2,048 tokens. These limits apply to all requests, including streaming and non-streaming. You can monitor your usage in the dashboard to avoid hitting limits. This predictable scaling makes our API ideal for production applications.