Building a custom MCP server for a newsletter platform
You send 50,000 input tokens and receive 2,000 output tokens. Cost = (50,000 / 1,000,000) * $0.15 + (2,000 / 1,000,000) * $0.50 = $0.0075 + $0.001 = $0.0085.
Unfiltered coding AI Pricing: Pay Per Token
Get uncensored coding AI pricing that stays flat regardless of traffic spikes. Pay only for the tokens your requests actually consume, with no hidden monthly fees or subscription traps.
- $0.15
- per 1M input tokens
- $0.50
- Output tokens / 1M
- 100,000
- token context
- $0.50
- trial credit
- 300
- requests per minute
Cost calculator
Worked examples
Generating a large, unrestricted creative writing scene
You send 10,000 input tokens and receive 16,000 output tokens. Cost = (10,000 / 1,000,000) * $0.15 + (16,000 / 1,000,000) * $0.50 = $0.0015 + $0.008 = $0.0095.
Running a batch of 100 short, unfiltered queries
Each query uses 1,000 input and 500 output tokens. Total input = 100,000 tokens ($0.015). Total output = 50,000 tokens ($0.025). Total cost = $0.04.
Transparent Token Pricing
We charge strictly by usage. Our unfiltered LLM costs are set at $0.15 per million input tokens and $0.50 per million output tokens. You never pay for idle time. Every request is billed based on the exact tokens consumed. Errors and refusals do not incur charges. This structure ensures your uncensored AI chat budget remains predictable. You can track every token in real-time through our dashboard.
Crypto Top-Ups and Bonus Credit
Add funds using USDT (TRC20) or USDC (Base). Minimum top-ups start at $20. We offer bonus credit to increase your purchasing power. Deposits of $50 earn a 5% bonus. Deposits of $100 earn a 10% bonus. Deposits of $200 earn a 15% bonus. Your prepaid balance never expires. There are no monthly subscription fees. This approach keeps our infrastructure lean and your costs low.
Trial Credit for New Accounts
New users receive $0.50 in trial credit. The trial lasts for 7 days. This allows you to test the uncensored coding AI performance immediately. You can use the trial to verify compatibility with your existing OpenAI-compatible SDKs. Once the trial expires, you must top up to continue using the API. Errors during the trial period are free.
Rate Limits and Request Sizes
Each API key supports 300 requests per minute. You can run up to 8 concurrent requests simultaneously. The maximum request body size is 8 MB. The context window allows 100,000 tokens total. You can generate up to 16,000 tokens per response. These limits prevent abuse while ensuring reliable performance. If you need higher throughput, you can generate additional API keys. Each key operates independently with its own limits.
Questions and answers
Does the unfiltered coding AI API charge for failed requests?
No. We do not charge for errors or refusals. You only pay for tokens that are successfully processed and returned. This applies to both input and output tokens. Failed requests are completely free.
What happens if I top up with crypto?
Your prepaid balance is credited immediately. The balance never expires. You can use the funds for any API request. Bonus credit is applied based on your deposit amount. You can track your balance in the dashboard.
Can I use the trial credit for coding tasks?
Yes. The trial credit works for all API requests. You can test the uncensored coding AI with your own code. The trial lasts for 7 days. Use the trial to verify compatibility.
What is the maximum output per request?
You can generate up to 16,000 tokens per request. The total context window is 100,000 tokens. This includes both input and output tokens. You can adjust the max_tokens parameter to control output length. Shorter outputs cost less.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
