Standard Token Rates
Our API charges $0.15 per million input tokens and $0.50 per million output tokens. This flat rate applies to all requests regardless of the model version or time of day. You only pay for the tokens processed, not for idle connections or API key maintenance.
Input tokens include your prompt, system instructions, and any context history sent to the endpoint. Output tokens cover the model's generated response. Streaming responses count both input and output tokens toward your total usage. Errors do not consume tokens if the request fails before generation starts.
Input vs. Output Costs
Input tokens cost less than output tokens because processing context is cheaper than generating text. You pay $0.15 per million input tokens versus $0.50 per million output tokens. This ratio matters most when you send long context windows with short responses.
A 10,000 token prompt with a 1,000 token response costs more than a 1,000 token prompt with a 10,000 token response. Optimize your system prompts to reduce input waste. Use efficient formatting to keep output lengths tight. Balance context length against generation depth to control costs.
Comparison with Major Providers
Major providers like OpenAI, Anthropic, and Google charge varying rates based on model tiers. Their pricing structures often include premium rates for larger context windows or faster inference. Proxy aggregators add their own markup on top of these base rates.
Our uncensored model offers a consistent rate without tiered pricing. You do not pay extra for longer context or higher temperature settings. Check the official documentation of other vendors for their current per-token rates. Our pricing remains stable regardless of demand spikes or model updates.
Prepaid vs. Subscription Models
Prepaid models eliminate monthly base fees and allow precise budget control. You load credit once and spend it as needed. Unused credit never expires, so you pay only for what you use.
Subscription models often charge a fixed monthly fee regardless of usage volume. This structure benefits heavy users but wastes money for occasional callers. Our prepaid approach aligns cost directly with token consumption. Top up when you need more capacity. No recurring charges appear on your statement.
Crypto Payment Bonuses
Top up your account with USDT on TRC20 or USDC on Base. Deposits between $20 and $500 qualify for bonus credit. A $50 deposit gives +5% bonus credit. A $100 deposit yields +10% bonus credit. A $200 deposit provides +15% bonus credit.
These bonuses effectively reduce your cost per token. The bonus credit expires at the same time as your base credit. Use crypto payments to maximize your total token volume.
Hidden Costs in Proxy Services
Proxy services often charge per request regardless of token count. They may add fees for failed requests or rate limit overages. Some aggregators route traffic through multiple models, increasing latency and cost.
Our direct API serves one uncensored model without routing layers. You pay only for tokens processed. Errors are free if no tokens are generated. This transparency prevents surprise charges on your monthly bill. Verify that your proxy service charges per token, not per call.
Scaling Your Token Usage
You can send up to 300 requests per minute and 8 concurrent requests per key. The request body limit is 8 MB. These limits support moderate scaling without immediate need for key rotation.
Use one API key per account. Generate a new key if you need to replace an old one. Streaming responses help manage memory usage during high-volume sessions. Monitor your token usage through the dashboard to avoid running out of credit unexpectedly. Adjust batch sizes to stay within the concurrent request limit.
Trial Credit Value
New accounts receive $0.50 in trial credit valid for seven days. This allows you to test the API with real tokens before committing to a larger deposit.
Use the trial to verify compatibility with your SDK. Test streaming responses and function calling. Check latency and response quality. The trial credit works exactly like paid credit. It does not expire after seven days if you do not use it. Use it within seven days to avoid losing it.
Final Cost Estimator
Calculate your expected spend by multiplying your input tokens by $0.15 and output tokens by $0.50. Divide by one million to get the dollar amount. Add any bonus credit from your crypto deposit to reduce the net cost.
Example: 1 million input tokens and 100,000 output tokens cost $0.15 + $0.05 = $0.20. A $100 deposit gives +10% bonus credit, totaling $110 in usable credit. Your effective cost per million combined tokens drops slightly. Use this formula to budget your monthly API usage accurately.
Common questions
What is the openai compatible API pricing for uncensored models?
Our uncensored API charges $0.15 per 1M input tokens and $0.50 per 1M output tokens. There are no monthly fees or base charges. You pay only for the tokens processed in each request.
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.
How do crypto bonuses affect my API costs?
Crypto top-ups from $20 to $500 include bonus credit. Deposits of $50, $100, and $200 yield +5%, +10%, and +15% bonus credit respectively. These bonuses increase your total token volume without extra cost.
Are there hidden fees for streaming or function calling?
No hidden fees exist for streaming or function calling. You pay standard token rates for both input and output. Errors do not consume tokens if the request fails before generation. All features use the same per-token pricing.
Obtain your API key in a single step
Register, retrieve your key, and update your base URL. That covers the entire configuration.
