Transparent pricing
Predictable billing without variable overhead or subscription traps. We charge strictly for what you consume, ensuring your per-token spend stays transparent.
No subscriptions. Prepaid balance does not expire.
Cost estimator
Usage examples
A chatbot processing a short user query and returning a concise answer.
Sending 2,000 input tokens and receiving 500 output tokens costs $0.305. The calculation is: (2,000 / 1,000,000 × 0.15) + (500 / 1,000,000 × 0.50) = $0.30 + $0.005 = $0.305.
A script summarizing a long document with detailed reasoning.
Processing 50,000 input tokens and generating 4,000 output tokens costs $7.75. The math is: (50,000 / 1,000,000 × 0.15) + (4,000 / 1,000,000 × 0.50) = $7.50 + $0.25 = $7.75.
A high-volume batch job analyzing customer support logs.
Ingesting 500,000 input tokens and producing 10,000 output tokens costs $80.00. The formula yields: (500,000 / 1,000,000 × 0.15) + (10,000 / 1,000,000 × 0.50) = $75.00 + $5.00 = $80.00.
1. The simple per-token rate
Our pricing is strictly linear based on token volume. You pay $0.15 per million input tokens and $0.50 per million output tokens. Errors do not consume your balance. Refusals are free. This structure eliminates hidden fees for failed requests.
Competitors often charge more for larger context windows. We offer a 100,000 token context window at the same base rate. Streaming responses via SSE include final token usage in the last chunk. You can track exact spend in real-time.
JSON mode and function calling use the same rates. There are no extra charges for tool usage. Your application logic scales without unpredictable cost spikes.
2. Prepaid credit and bonus tiers
Prepaid credit keeps your spending predictable. You load funds once and consume them as needed. Credit never expires. You avoid monthly subscription traps entirely. No minimum spend is required.
We offer bonus credit for larger top-ups. Deposits of $50 to $99 receive a 5% bonus. Amounts from $100 to $199 get a 10% bonus. Payments of $200 to $500 earn a 15% bonus. This reduces your effective cost per token significantly.
A new account receives $0.50 in trial credit. This credit is valid for 7 days. You can test the API before committing to a larger balance.
3. Crypto payment methods
We accept only cryptocurrency for simplicity. USDT on the TRC20 network is supported. USDC on the Base network is also available. The system applies your bonus automatically. Mistakes like double charges are fixed via the Support page.
Privacy is maintained through email-only accounts. Your prompts are not used for training. The lack of traditional payment processors reduces friction for global developers.
Common questions
What is the LLM inference cost for uncensored chat applications?
Input tokens cost $0.15 per million and output tokens cost $0.50 per million. This rate applies to our uncensored model running on our own servers. Errors and refusals do not incur charges.
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 does the prepaid credit system work?
Credit is charged based on real token usage. Your balance decreases only when tokens are consumed. Unused credit never expires. You can switch between models or features without losing your balance.
Are there any hidden fees or subscription traps?
There are no monthly fees or hidden costs. You pay only for what you use. The base URL is compatible with standard OpenAI SDKs. You can integrate easily without vendor lock-in.
Secure your API key
Register, copy the key, and update your base URL. That is all.
