Simple, transparent api pricing
Get the cheapest LLM API for uncensored chat completions. We charge $0.15 per million input tokens and $0.50 per million output tokens with no monthly subscriptions or hidden fees.
- $0.15
- per 1M input tokens
- $0.50
- Output tokens / 1M
- 100,000
- token context
- $0.50
- trial credit
- 300
- requests per minute
Cost estimator
Usage examples
- CLI coding assistant generating code snippets
- A prompt containing 4,000 tokens generates 1,500 tokens of code. The input cost is 4 * 0.15 = $0.0006. The output cost is 1.5 * 0.50 = $0.00075. The total cost for this request is $0.00135.
- Uncensored roleplay with long context
- A user sends a 50,000 token conversation history to generate a 2,000 token response. Input cost is 50 * 0.15 = $7.50. Output cost is 2 * 0.50 = $1.00. Total cost is $8.50.
- High-volume data extraction
- Processing 100 requests with 2,000 input tokens each and 500 output tokens each. Input cost is (100 * 2 * 0.15) = $30.00. Output cost is (100 * 0.5 * 0.50) = $25.00. Total cost is $55.00.
Pay-per-use token pricing
Our API uncensored service charges strictly for the tokens you process. You pay $0.15 per million input tokens and $0.50 per million output tokens. Errors and refusals do not consume credit, so you only pay for successful completions. This model eliminates waste from failed requests. You can track usage in real time through the dashboard. Prepaid credit is deducted immediately upon token consumption. Errors during processing are completely free. This ensures you never pay for broken responses. The model handles context windows up to 100,000 tokens efficiently. Output limits are set to 16,000 tokens per request. Smaller outputs default to 2,048 tokens if not specified. Streaming responses include token counts in the final chunk. This transparency helps you budget accurately. Function calling and JSON mode work without extra fees. Parameters like temperature and top_p do not affect pricing. You get full control over your spending. No minimum spend is required for any transaction. Every token counts toward your balance. This approach keeps costs predictable for developers.
Prepaid credit and no expiration
Prepaid credit never expires, so you can top up once and use it over months. There are no monthly subscriptions or renewal fees to manage. You pay only for what you use, avoiding wasted money on unused quotas. Your balance remains stable until you decide to spend it. This structure suits projects with irregular traffic patterns. Large batches of requests do not trigger sudden price hikes. You maintain full control over your API key and spending limits. Credit is charged by real token usage, ensuring fairness. Errors and refusals are free, so bad requests do not drain your balance. This prepaid model allows you to forecast expenses accurately. You can switch to a new API key without losing your existing credit. One active key per account simplifies management. The system tracks usage precisely down to the token. This reliability makes budgeting straightforward for hobbyists and teams alike.
Crypto top-ups with bonus credits
We accept crypto only for top-ups, offering bonus credits for larger deposits. You can deposit any whole amount between $20 and $500 using USDT on TRC20 or USDC on Base. Deposits of $50 or more earn a 5% bonus. Deposits of $100 or more earn a 10% bonus. Deposits of $200 or more earn a 15% bonus. This bonus credit applies to your prepaid balance immediately. This method reduces transaction fees and processing delays. You get more value for your cryptocurrency. The process is simple and transparent. Top-ups are processed quickly to keep your API running. You can continue building without waiting for traditional payment confirmations. This crypto-first approach aligns with the uncensored nature of the service. It ensures privacy and speed for all transactions. Your bonus credits are permanent and do not expire.
Free trial credit for new accounts
Every new account receives $0.50 of trial credit valid for 7 days. This allows you to verify the uncensored model works for your project. You can send requests and see how tokens are consumed. The trial credit helps you evaluate latency and accuracy. It is one per person, so use it wisely. After the trial expires, you can top up with crypto. The trial gives you a risk-free way to integrate the API. You can test streaming, function calling, and JSON mode. This trial is perfect for developers checking compatibility. It does not require phone verification or personal data. Your email is the only requirement for signup. This low barrier to entry encourages experimentation. You can switch to a paid plan whenever ready.
Request and rate limits
Each API key supports 300 requests per minute and 8 concurrent requests. The maximum request body size is 8 MB. These limits ensure stable performance for all users. You can monitor your usage in the dashboard to avoid throttling. If you need higher limits, contact support. The system handles streaming responses efficiently. Token counts are included in the final chunk of streaming responses. This helps you track usage accurately. Function calling and JSON mode do not count against concurrency limits differently. Parameters like temperature and top_p do not affect limits. The 100,000 token context window is fully supported. Output limits are set to 16,000 tokens per request. Smaller outputs default to 2,048 tokens if not specified. This structure allows for flexible use cases. You can build chat apps or coding assistants without worrying about sudden bottlenecks. The API is designed for reliability and speed.
Billing and refunds
Credit is not refunded once used, as it never expires. If you experience a double charge or error, contact support via the Support page. Mistakes are fixed promptly to ensure fairness. Your prepaid balance remains intact until consumed. Errors and refusals are free, so you do not pay for bad requests. This billing model is transparent and straightforward. You can track every token consumed in real time. The dashboard provides detailed usage reports. You can export data for accounting purposes. This clarity helps developers manage their projects efficiently. No hidden fees or sudden price changes occur. The prepaid model ensures you always know your spend. Crypto top-ups are processed quickly. Bonus credits are applied immediately. This system supports both small hobbyists and large-scale applications. You can trust the billing to be accurate and fair.
Common questions
How does the uncensored API price compare to other providers?
Our pricing is $0.15 per million input tokens and $0.50 per million output tokens. This is among the cheapest LLM API options available for uncensored inference. You pay only for what you use, with no monthly subscriptions or hidden fees.
What is the deep seek API price for uncensored usage?
We charge $0.15 per million input tokens and $0.50 per million output tokens. Errors and refusals are free, so you only pay for successful completions. This pricing applies to all requests, regardless of length or complexity.
Which payment methods do you accept?
Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.
How do text-to-speech APIs typically price usage, and how does that compare to this API?
Text-to-speech APIs usually price by characters or seconds of audio. Our API prices by tokens, with input at $0.15 per million tokens and output at $0.50 per million tokens. This token-based model is standard for LLMs and allows precise cost tracking for text generation.
Retrieve your API key
Sign up, copy the token, update your base URL. That is all.
Try with trial credit