Transparent Token Pricing
Pay only for the exact tokens your model generates, with no monthly subscriptions or hidden fees. We strip away the bloat so you get raw inference power at the cheapest LLM API rates available.
- per 1M input tokens
- $0.15
- Output tokens / 1M
- $0.50
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
Usage examples
A Python script processes a 40,000-token context window for a technical summary task.
Sending 30,000 input tokens costs $0.15 * 30,000 / 1,000,000 = $0.0045. Generating 5,000 output tokens costs $0.50 * 5,000 / 1,000,000 = $0.0025. The total request cost is $0.0070. Errors during this process are free.
An automated coding agent runs 1,000 requests to refactor legacy code.
Each request uses 5,000 input tokens and 200 output tokens. Input cost: 5,000/1,000,000 * $0.15 = $0.00075. Output cost: 200/1,000,000 * $0.50 = $0.0001. Total per call is $0.00085. For 1,000 calls, you pay $0.85 total.
A research tool analyzes 10,000 tokens of security logs for anomalies.
Processing 8,000 input tokens costs $0.15 * 8,000 / 1,000,000 = $0.0012. Returning 1,000 output tokens costs $0.50 * 1,000 / 1,000,000 = $0.0005. The total is $0.0017.
Pay-Per-Use Rates
Our uncensored LLM charges exactly what you consume. You never pay for idle capacity or reserved slots. The base rate for input tokens is $0.15 per million tokens. Output tokens cost $0.50 per million tokens. This transparent model lets you predict costs down to the cent.
Errors do not consume credit. If the server returns an error, you keep your balance intact. This prevents the token apocalypse where bad network calls drain your budget. You only pay for successful generations that reach the client.
Crypto Top-Up Bonuses
Prepaid credit never expires. You can top up using USDT on TRC20 or USDC on Base. Minimum top-up is $20. Maximum is $500 per transaction. We offer bonus credit to reward larger deposits. A $50 deposit gives you +5% extra. A $100 deposit gives you +10% extra. A $200 deposit gives you +15% extra.
This crypto-only approach keeps overhead low. We avoid bank fees and chargebacks. Your credit sits in your account until you use it. There are no monthly fees to maintain access. You control the flow of funds.
Free Trial Credit
New accounts receive $0.50 of trial credit. This balance lasts for 7 days. You can test the uncensored AI capabilities without adding payment methods. Just sign in with Google or email to get your key.
Use this credit to verify the 100,000 token context window. Test function calling and streaming. If the model suits your needs, top up with crypto to continue. The trial is one per person. It proves the system works before you commit funds.
FAQ
How do I calculate the LLM token cost for my next API call?
Use the formula: (input_tokens / 1,000,000 * 0.15) + (output_tokens / 1,000,000 * 0.50). For example, 100k input tokens and 10k output tokens cost $15.00 + $5.00 = $20.00. Errors in the request do not add to this total.
Does the uncensored LLM model refuse content?
The model is tuned to answer without refusals for lawful adult use. It does not filter controversial or sexual topics. The only hard limit is sexual content involving minors. Requests violating this rule are refused.
What happens if I exceed the rate limits?
The API allows 300 requests per minute per key. It also limits concurrency to 8 requests at the same time. Exceeding these limits returns a 429 error. The request still counts toward your token usage if it succeeds.
Can I get a refund for my prepaid credit?
Credit is not refunded once purchased. It never expires, so you can use it whenever you need it. If you experience a double charge, contact Support to fix the balance.
Get your key instantly
Sign up, grab your API key, and update your base URL. That’s it.
