Compatible AIPricing
Open ai compatible API pricing
We charge exactly $0.15 per million input tokens and $0.50 per million output tokens. This transparent, prepaid-only structure eliminates monthly subscriptions and surprise fees.
- per 1M input tokens
- $0.15
- Output tokens / 1M
- $0.50
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
No subscription. Prepaid credit does not expire.
Cost estimator
Usage examples
A research assistant summarizing a 10,000-token document.
Cost = (10,000 / 1,000,000 * 0.15) + (2,048 / 1,000,000 * 0.50) = $0.0015 + $0.001024 = $0.002524.
A chatbot handling a 50,000-token context window with a 16,000-token response.
Cost = (50,000 / 1,000,000 * 0.15) + (16,000 / 1,000,000 * 0.50) = $0.0075 + $0.008 = $0.0155.
A local-first stack making 100 small requests of 1,000 input tokens each.
Cost = 100 * [(1,000 / 1,000,000 * 0.15) + (512 / 1,000,000 * 0.50)] = 100 * (0.00015 + 0.000256) = $0.0406.
Per-token pricing
We bill strictly on actual usage. You pay $0.15 per million input tokens and $0.50 per million output tokens. Errors and refusals cost nothing. We do not charge for unused capacity or idle time.
This model suits bursty workloads better than fixed subscriptions. You only pay for what you process. Our uncensored model handles diverse inputs without premium fees for specific content types.
Base requests include a default output limit. Setting max_tokens controls your spend precisely. You can stream responses to monitor token consumption in real-time.
Prepaid credit & bonuses
Add funds using USDT (TRC20) or USDC (Base). Minimum top-ups start at $20. We offer bonus credit for larger deposits. You receive +5% bonus for $50, +10% for $100, and +15% for $200.
Your credit never expires. This stability allows long-term projects without renewal anxiety. Errors during processing do not deduct from your balance.
Support handles double-charge corrections directly. Your prepaid balance remains available until you consume it.
Limits and constraints
Each API key supports 300 requests per minute. You can run 8 concurrent requests simultaneously. The maximum request body size is 8 MB.
Our context window accommodates 100,000 tokens total. Default outputs cap at 2,048 tokens unless you specify a higher limit. We enforce these limits to ensure consistent performance.
One active key per account simplifies tracking. Generating a new key replaces the old one immediately. This design prevents credential sharing issues.
Common questions
Is there a free tier?
New accounts receive $0.50 in trial credit valid for 7 days. This trial allows you to test the uncensored model before topping up.
How do I pay?
We accept only crypto: USDT on the TRC20 network or USDC on the Base network. Minimum deposits start at $20.
Do prices change?
Our per-token rates remain fixed at $0.15 for input and $0.50 for output. Bonuses scale with your deposit amount. We do not implement dynamic pricing based on demand.
Are errors charged?
No. If a request fails due to server issues or timeout, we do not charge for those tokens. You only pay for successfully processed tokens.
