Long-form creative writing with deep context
Processing a 50,000 token context window with 2,000 output tokens costs $0.15 * 50,000 / 1,000,000 + $0.50 * 2,000 / 1,000,000 = $0.0075 + $0.001 = $0.0085.
Transparent Token Pricing for Uncensored API
Pay only for what you consume with heretic LLM models, where your prepaid credit never expires and errors cost nothing. Our transparent token rates eliminate the surprise fees of monthly subscriptions.
Prepaid model. Credits do not expire.
- $0.15per 1M input tokens
- $0.50Output tokens / 1M
- 100,000token context
- $0.50trial credit
- 300requests per minute
Usage estimator
Usage examples
High-volume data extraction tasks
Analyzing 10,000 input tokens to extract 500 output tokens requires $0.15 * 10,000 / 1,000,000 + $0.50 * 500 / 1,000,000 = $0.0015 + $0.00025 = $0.00175.
Complex function calling with tools
Handling 15,000 input tokens for structured JSON output of 1,000 tokens uses $0.15 * 15,000 / 1,000,000 + $0.50 * 1,000 / 1,000,000 = $0.00225 + $0.0005 = $0.00275.
Token Rates and Costs
The uncensored models API charges $0.15 per 1M input tokens and $0.50 per 1M output tokens. This straightforward pricing structure ensures you pay strictly for the data processed by the abliterated models. Unlike opaque per-request billing, every token contributes directly to the cost. You can predict expenses accurately based on your usage patterns. Errors and refusals incur no charge, so your balance remains intact. The context window supports up to 100,000 tokens, allowing for deep context analysis without penalty. This model suits developers who need consistent, predictable costs for their LLM integrations.
Prepaid Credit and Top-ups
Prepaid credit is charged by real token usage, ensuring that every cent goes toward actual processing. Errors are free, meaning you never pay for failed requests or content refusals. Your credit never expires, allowing you to top up when convenient without losing funds. You can add whole amounts between $20 and $500, with bonus credit increasing as you spend more. This approach eliminates monthly subscription overhead and gives you full control over your budget. Start with a free trial, then top up seamlessly using crypto.
Free Errors and Trial Credit
Errors during processing are free, so you can test the uncensored API without financial risk. This trial allows you to verify the abliterated models meet your needs before committing to a larger top-up. If you make a mistake like a double charge, support can fix it via the Support page. The prepaid balance keeps your spending predictable, with no hidden fees or subscription traps. Use this time to explore function calling and streaming capabilities.Common questions
What is the cost per token for uncensored models?
Input tokens cost $0.15 per 1M tokens, while output tokens cost $0.50 per 1M tokens. Errors are free, so you only pay for successful processing. This transparent model ensures you know exactly what you are spending on each request.
Does the prepaid credit expire?
No, your prepaid credit never expires. You can top up at any time, and any unused balance remains available for future requests. This flexibility allows you to manage your budget without the pressure of monthly subscription deadlines.
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.
Can I get a refund for my credit?
Credit is not refunded as it never expires and is charged by real usage. If you experience a double charge or other issue, you can resolve it through the Support page. This system ensures that your balance remains accurate and reflects your actual usage patterns.
Secure your API key
Register, retrieve your key, update the endpoint. Minimal config required.
