Deep research summarization
A 40k-token research paper processed for a 2k-token summary. Input: 40,000 tokens × $0.25/1M = $0.01. Output: 2,000 tokens × $1.00/1M = $0.002. Total: $0.012.
Stop guessing your bill. Our pay-as-you-go LLM API charges strictly for tokens consumed, with transparent per-million pricing and no hidden subscription fees.
No subscription. Prepaid credit never expires.
A 40k-token research paper processed for a 2k-token summary. Input: 40,000 tokens × $0.25/1M = $0.01. Output: 2,000 tokens × $1.00/1M = $0.002. Total: $0.012.
Generating a 3,000-word story (approx. 4k tokens) from a short prompt (500 tokens). Input: 500 tokens × $0.25/1M = $0.000125. Output: 4,000 tokens × $1.00/1M = $0.004. Total: $0.004125.
Five rapid-fire requests to test uncensored model behavior, each with 100 tokens input and 50 tokens output. Input: 500 tokens × $0.25/1M = $0.000125. Output: 250 tokens × $1.00/1M = $0.00025. Total: $0.000375.
Our pricing model is strictly token-based, reflecting the actual compute resources your requests consume. We charge $0.25 per 1 million input tokens and $1.00 per 1 million output tokens. This structure is standard for modern LLM APIs, but we ensure you always know exactly what you are paying for. Input tokens cover your prompt and context window usage, while output tokens cover the model's generated response. Because we run a single uncensored model, you never pay for idle capacity or unused model tiers. The ratio of input to output tokens varies by use case, but the math remains consistent: cost equals tokens divided by one million, multiplied by the rate. This transparency allows you to budget precisely for high-volume text generation tasks without worrying about hidden egress fees or request-count penalties.
We operate on a prepaid credit system, meaning you load funds once and spend them as needed. There are no monthly subscriptions, no auto-renewing plans, and no credit card holds. Your API key works immediately upon funding, and usage deducts from your balance in real-time. This model keeps your spend predictable: you cannot exceed what you have loaded. If your balance reaches zero, requests stop until you top up. This is ideal for developers who want to control costs strictly or test the uncensored model without committing to a recurring bill. You can add funds via crypto (USDT or USDC) starting at $10, and your credit never expires. This approach eliminates the friction of vendor lock-in and ensures you only pay for the compute you actually use.
To reward higher usage, we offer bonus credits on top of your loaded funds. When you purchase $50 or more, you receive a 5% bonus credit. At $100 or more, the bonus increases to 10%. These bonus credits are added to your account immediately and can be used for API requests just like your base funds. This effectively lowers your effective cost per token for larger loads. For example, a $100 purchase gives you $110 in usable credit. The bonus does not expire separately; it follows the same non-expiring rule as your base balance. This structure rewards volume without requiring a long-term contract, making it easy to scale your uncensored LLM usage as your project grows.
One price list, one set of limits, all features on every key.
| Feature | Support |
|---|---|
| Max output | 16,000 tokens max; 2,048 if max_tokens is not set |
| Function calling | Supported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages |
| JSON mode | JSON object mode via response_format json_object |
| Max context | 64,000 tokens, input and output combined |
| Concurrency | up to 8 in parallel per key |
| Requests per minute | 300/min per key |
| Subscription | no monthly fee; paid credit does not expire |
| Bonus credit | +5% from $50, +10% from $100 |
| Free trial | $0.50 of credit valid 7 days, no card needed |
| Top-up | USDT (TRC20) or USDC (Base), any whole amount from $10 to $500 |
| Token prices | $0.25 per 1M input tokens · $1.00 per 1M output tokens |
No. Once you purchase credits, they do not expire regardless of how much time passes. You can load funds today and use them months later without losing your balance.
Our system checks your balance before processing. If your balance is insufficient, the request will be rejected, ensuring you never go into debt. You cannot spend more than you have loaded.
Bonus credits are automatically applied when you purchase $50 or more (5% bonus) or $100 or more (10% bonus). You do not need to enter a code; the credit is added to your account immediately after payment.
No. There are no monthly fees, no per-request fees, and no hidden charges. You only pay for the tokens consumed by your input and output. The only cost is the token usage itself.
Create an account, copy the key, change the base URL. That is the whole setup.