A developer testing a single turn for a 2048-token reply.
Input: 1,000 tokens ($0.00015). Output: 2,048 tokens ($0.001024). Total: $0.001174.
Best LLM API/Transparent pricing for uncensored inference
Pay only for what you process with transparent per-token rates. Our uncensored API removes subscription friction so your budget stays predictable.
No subscription. Prepaid credit never expires.
Input: 1,000 tokens ($0.00015). Output: 2,048 tokens ($0.001024). Total: $0.001174.
Input: 50,000 tokens ($0.0075). Output: 4,096 tokens ($0.002048). Total: $0.009548.
Input: 90,000 tokens ($0.0135). Output: 8,192 tokens ($0.004096). Total: $0.017596.
We charge strictly by actual token usage. Your prepaid balance decreases only when tokens are processed. Errors cost nothing. This structure keeps your spend predictable. You never pay for idle time. Input tokens cost $0.15 per 1M tokens. Output tokens cost $0.50 per 1M tokens. The formula is: (input_tokens / 1,000,000) * 0.15 + (output_tokens / 1,000,000) * 0.50. This simple math applies to every request. No hidden fees exist. Your credit covers exactly what you use.
Top up using USDT on TRC20 or USDC on Base. We offer bonuses for larger deposits. A $50 top-up gives +5% credit. A $100 top-up gives +10% credit. A $200 top-up gives +15% credit. You can top up any whole amount from $20 to $500. These bonuses stretch your budget further. Your credit never expires. You control your exact spending limit. This approach avoids monthly subscription traps. You only pay for the inference you actually run.
New accounts receive $0.50 in trial credit. This credit lasts for 7 days. Errors and refusals do not consume your balance. Mistakes like double charges are fixed via Support. Your prepaid credit remains valid indefinitely. This policy lets you test the uncensored model risk-free. You can verify token counts and pricing accuracy. Start with the trial to confirm the setup works. Then top up with crypto to continue.
We enforce clear limits to ensure stability. You can send 300 requests per minute. Only 8 requests run simultaneously per key. The maximum request body size is 8 MB. Each account holds one active key. Generating a new key replaces the old one. These limits support steady development workflows. Large batch jobs may need to pace their requests. The 100,000 token context window fits within these constraints. Adjust your concurrency to stay within the 8 concurrent request limit. This ensures consistent performance for your uncensored API calls.
No. We use a prepaid credit model. You top up with crypto and pay only for the tokens you consume. Your credit never expires.
We accept USDT on TRC20 and USDC on Base. Top-ups range from $20 to $500.
No. Errors and refusals are free. Your balance only decreases when tokens are successfully processed. This keeps your costs accurate.
Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.
Register, retrieve your key, update the endpoint. That is all.