Batch processing short documents
You send 500,000 input tokens to classify text and receive 50,000 output tokens. Cost = (500,000 / 1,000,000 * 0.15) + (50,000 / 1,000,000 * 0.50) = $0.075 + $0.025 = $0.10.
The cheapest LLM API for uncensored AI generation charges only for what you use, with transparent per-token rates and no monthly subscriptions.
No subscription. Prepaid credit does not expire.
You send 500,000 input tokens to classify text and receive 50,000 output tokens. Cost = (500,000 / 1,000,000 * 0.15) + (50,000 / 1,000,000 * 0.50) = $0.075 + $0.025 = $0.10.
A single request uses 50,000 input tokens and generates 1,000 output tokens. Cost = (50,000 / 1,000,000 * 0.15) + (1,000 / 1,000,000 * 0.50) = $0.0075 + $0.0005 = $0.008.
Your app processes 2,000,000 input tokens and produces 400,000 output tokens. Cost = (2,000,000 / 1,000,000 * 0.15) + (400,000 / 1,000,000 * 0.50) = $0.30 + $0.20 = $0.50.
The uncensored AI API charges strictly by usage. You pay $0.15 per million input tokens and $0.50 per million output tokens. Errors do not consume credit. This prepaid balance keeps spend predictable because you only fund what you actually need.
Add credit via USDT (TRC20) or USDC (Base). Minimum top-up is $20. You receive a +5% bonus at $50, +10% at $100, and +15% at $200. Credits never expire.
New accounts get $0.50 trial credit valid for 7 days. Sign up with Google or email to get your API key immediately. Use this to test the uncensored model before committing to a crypto top-up.
The codex key costs $0.15 per million input tokens and $0.50 per million output tokens. You pay only for what you use, with no hidden fees or monthly subscriptions.
Top up using USDT (TRC20) or USDC (Base). We accept amounts from $20 to $500. You receive bonus credit based on your top-up tier. Credit is charged by real token usage.
Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.
You get 300 requests per minute and 8 concurrent requests per key. Each request body is limited to 8 MB. The uncensored model supports up to 100,000 tokens context window.
Register, copy the key, update your base URL. That’s the entire configuration.