Pay per token, no subscriptions
Stop paying monthly fees for idle capacity. Our prepaid token billing ensures you only fund the exact inference you execute.
- $0.15per 1M input tokens
- $0.50Output tokens / 1M
- 100,000token context
- $0.50trial credit
- 300requests per minute
No subscription required. Prepaid balance does not expire.
Cost estimator
Pricing examples
Batch processing 100,000 tokens of raw text for analysis
You pay strictly for the tokens processed. Input: 100,000 tokens at $0.15 per 1M equals $0.015. No output is generated yet, so the total cost is $0.015.
Streaming a detailed creative story response
Input: 5,000 tokens ($0.00075) + Output: 2,000 tokens ($0.00100). Total cost: $0.00175 for the complete exchange.
High-volume utility function calls with short answers
Input: 10,000 tokens ($0.00150) + Output: 500 tokens ($0.00025). Total cost: $0.00175. Errors consume no tokens, so you do not pay for failed attempts.
How prepaid credit works
Your API key activates a prepaid balance that deducts real tokens instantly. You top up via crypto and never pay monthly fees for unused capacity. Errors and refusals consume zero tokens, so you only fund successful inference. The prepaid balance keeps spend predictable because you control the exact amount loaded. No subscription lock-in means you can stop funding anytime without penalties.
Trial credit for new accounts
Every new account receives $0.50 of trial credit valid for 7 days. This trial allows you to test the uncensored model with real latency and throughput. The credit never expires, so you can use it at your own pace. No phone number is required to claim this initial balance.
Why prepaid keeps spend predictable
Prepaid credit eliminates the shock of unexpected monthly bills. You see the exact cost of each request before it happens. Errors are free, so you do not pay for bad inputs. The prepaid balance ensures you never overspend your budget. You can top up small amounts frequently or large amounts for long-term projects. This model suits developers who need precise cost control.
Frequently asked questions
What is open router AI pricing compared to standard models?
Our uncensored model charges $0.15 per 1M input tokens and $0.50 per 1M output tokens. You only pay for the tokens actually used. Errors do not incur any cost. This structure is often cheaper than subscription-based alternatives for burst workloads.
How do I top up my balance?
You can top up using USDT (TRC20) or USDC (Base). Any whole amount from $20 to $500 is accepted. The payment is processed instantly upon confirmation. Your balance updates immediately for use with the API.
Do I lose my credit if I stop using the API?
No, your prepaid credit never expires. You can leave it in your account indefinitely. There are no monthly maintenance fees to drain your balance. You can resume using it whenever you need more uncensored responses.
Can I get a refund for my prepaid credit?
Credit is not refunded once loaded. If you experience a double charge or error, you can request a fix via the Support page. The balance remains in your account for future use. This policy applies to all standard transactions.
Generate your key in seconds
Register, retrieve your key, and point your client to the new base URL. It is that simple.
Create key