apillmsourceopen.comCosts
Transparent prepaid pricing for uncensored generation
We charge exactly $0.15 per million input tokens and $0.50 per million output tokens, with no hidden fees or subscriptions. You top up with crypto and pay only for the tokens your model actually generates.
No subscriptions. Prepaid balance does not expire.
- $0.15per 1M input tokens
- $0.50Output tokens / 1M
- 100,000token context
- $0.50trial credit
- 300requests per minute
Cost estimator
Pricing examples
Standard uncensored chat completion
A 10,000 token prompt and an 8,000 token response costs $0.0015 + $0.004 = $0.0055. You only pay for the tokens that successfully return.
Long-context analysis
Feeding 50,000 tokens of context with a 4,000 token output costs $0.0075 + $0.002 = $0.0095. Errors and refusals are free, so you never pay for wasted effort.
High-volume streaming
Sending 20,000 input tokens and receiving 16,000 output tokens (the max) costs $0.003 + $0.008 = $0.011 per request. Streaming tokens via SSE are billed exactly as they arrive.
Per-Token Pricing: Input vs. Output
Transparent input and output rates
We charge $0.15 per million input tokens and $0.50 per million output tokens. This structure reflects the different computational costs of processing your prompt versus generating text. Input tokens are cheaper because the model reads your data. Output tokens cost more because the server performs active inference for every token produced. You can predict your exact bill by tracking token counts in the API response headers.
This model avoids the complexity of per-model pricing tiers. Every request uses the same uncensored open-weight model, so you never wonder which pricing tier applies. You simply multiply the tokens used by the fixed rates. Errors do not consume credit, ensuring you pay for actual work done.
Prepaid Credit: Pay Only for What You Use
Our prepaid system eliminates monthly subscription waste. You buy a balance of credit and spend it as your requests arrive. Unused credit never expires, so you can pause usage and return later without penalty. This approach keeps your LLM costs strictly variable and predictable.
When you integrate the API, you simply check your balance before major runs. Since errors are free, your actual spend is often lower than your token usage might suggest.
Crypto Top-Ups: USDT (TRC20) and USDC (Base)
We accept only USDT on the TRC20 network or USDC on the Base network. Minimum top-ups start at $20 and go up to $500 per transaction. This reduces friction and keeps your billing private.
Top-ups are processed instantly once the blockchain confirms the transaction. You can add any whole dollar amount between the limits. Our system automatically converts your crypto to usable API credit. You can manage your keys and view your balance directly after signing in with Google or email.
Frequently asked questions
How is the cost calculated for a single request?
Cost equals (input_tokens / 1,000,000 * 0.15) + (output_tokens / 1,000,000 * 0.50). You pay for every token the model successfully generates. Refusals and errors consume zero credit.
Do I lose my credit if I don't use it?
No, your prepaid credit never expires. You can top up today and use the balance months later. There are no monthly fees or subscription renewals to manage.
What payment methods do you accept for top-ups?
We accept USDT (TRC20) and USDC (Base) only. Minimum top-ups are $20 and maximums are $500.
Is there a free tier or trial available?
Every new account receives $0.50 of trial credit valid for 7 days. This allows you to test the uncensored model before buying a larger balance.
Get your API key
Sign up, copy the key, point to our base URL. Done.
