Token pricing breakdown
Our uncensored LLM API charges strictly per token used. Input tokens cost $0.15 per million, while output tokens cost $0.50 per million. Errors and refusals incur no charge. This structure ensures you pay only for the compute your request consumes.
- Input: $0.15 / 1M tokens
- Output: $0.50 / 1M tokens
You can predict costs exactly before sending requests. The ratio between input and output determines your total spend. Longer contexts increase input costs linearly. Higher creativity settings may increase output tokens.
Prepaid credit and no expiry
Prepaid credit covers all token usage without monthly fees. Your balance decreases only when tokens are processed. Unused funds remain available indefinitely. This model eliminates waste from unused subscription tiers.
You top up via crypto only. The balance updates immediately after confirmation. Errors do not deduct from your credit. This approach keeps your operational costs predictable and transparent.
Crypto payment options and bonuses
Crypto payments offer instant top-ups with bonus credit. USDT on TRC20 and USDC on Base are accepted. Minimum top-up is $20. Maximum is $500 per transaction. This method ensures fast processing and lower fees for both parties. Your bonus credit is added immediately to your account balance.
Trial credit details
New accounts receive $0.50 of trial credit. This amount is valid for seven days. You can test the uncensored model immediately. This trial allows you to verify API compatibility before committing funds.
The trial credit is non-refundable. It expires after seven days if unused. You can generate a new account to receive another trial. This feature lets developers evaluate the API without financial risk.
Request limits and quotas
Rate limits protect service stability for all users. Each key supports 300 requests per minute. Concurrency is limited to eight simultaneous requests. The request body must not exceed 8 MB. These limits ensure fair access during peak usage.
You receive one active key per account. Generating a new key replaces the previous one. This design simplifies key management for most developers. Adjust your client library to respect these quotas.