Processing a batch of user messages for a roleplay chatbot
Input: 500,000 tokens × $0.15 = $0.075. Output: 200,000 tokens × $0.50 = $0.100. Total cost: $0.175. You only pay for what the model actually processes.
Transparent uncensored API pricing
Get uncensored API pricing that charges by the token, not by the seat. Our prepaid balance covers every request with transparent per-token rates and zero monthly subscriptions.
per 1M tokens
per 1M input tokens$0.15
Output tokens / 1M$0.50
token context100,000
trial credit$0.50
requests per minute300
No subscriptions. Prepaid balance does not expire.
Pricing calculator
Pricing examples
Running a long-form creative writing assistant
Input: 10,000 tokens × $0.15 = $0.0015. Output: 16,000 tokens × $0.50 = $0.008. Total cost: $0.0095. High output limits allow deep generation without extra fees.
Handling technical support queries with tool usage
Input: 1,000,000 tokens × $0.15 = $0.15. Output: 500,000 tokens × $0.50 = $0.25. Total cost: $0.40. Function calling costs are included in the standard token rates.
Pay-per-use token rates
Direct model pricing
Every request costs exactly what the tokens weigh. We do not route your traffic through other providers, so you pay our base rates directly. Input tokens arrive at $0.15 per million tokens. Output tokens arrive at $0.50 per million tokens. You can stream responses via SSE and track usage in the final chunk. There are no hidden fees for streaming or function calling. Errors and refusals cost nothing. Your prepaid credit covers real usage only. You never pay for downtime.
Prepaid credit and crypto bonuses
Crypto top-ups with bonuses
Add funds using USDT on TRC20 or USDC on Base. We accept whole amounts from $20 to $500. You get a 5% bonus for $50 deposits. You get a 10% bonus for $100 deposits. You get a 15% bonus for $200 deposits. Your credit never expires. Mistakes like double charges are fixed via the Support page. You control your spend with a prepaid balance. This keeps your API costs predictable for any project.
Rate limits and request costs
Consistent limits per key
You get 300 requests per minute per key. You can run 8 requests simultaneously per key. The request body limit is 8 MB. Each account holds one active key. A new key replaces the old one. The model handles a 100,000 token context window. Max output is 16,000 tokens per request. JSON mode and tool calling work seamlessly. You pay for tokens, not for the complexity of your prompt structure.
FAQ
What is the uncensored LLM API pricing for high volume?
You pay $0.15 per million input tokens and $0.50 per million output tokens. There are no volume tiers or tiered discounts. You get the same low rate regardless of how many tokens you process. This applies to all requests, including streaming and tool usage.
Which payment methods do you accept?
Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.
Is this an openai compatible API gateway?
Yes. We use the standard chat-completions endpoint. You can use the official OpenAI SDKs by changing the base_url. Our model id is 'uncensored'. It is not GPT, Claude, or Gemini. It is an open-weight model run on our own servers. It provides direct privacy and consistent availability.
How does prepaid credit keep spend predictable?
You top up with crypto and your balance covers all usage. You stop spending when the balance runs out. There are no monthly subscriptions or minimum fees. Errors and refusals are free. This model works well for projects with variable traffic. You pay only for what you consume.
Generate your API key
Sign up, copy the key, update the base URL. Simple as that.
