Long-form adult novel writing
Input 30,000 tokens (including character settings and context), output 5,000 tokens (generated chapter content). Calculation: (30,000 / 1,000,000 * $0.25) + (5,000 / 1,000,000 * $1.00) = $0.0075 + $0.005 = $0.0125.
Da Moxing api uses a pure pay as you go model with no monthly fee or subscription threshold. Your prompt defines the content, and the price is determined by usage, transparent and predictable.
No subscription. Prepaid credit never expires.
Input 30,000 tokens (including character settings and context), output 5,000 tokens (generated chapter content). Calculation: (30,000 / 1,000,000 * $0.25) + (5,000 / 1,000,000 * $1.00) = $0.0075 + $0.005 = $0.0125.
Input 20,000 tokens (long conversation history), output 2,000 tokens (character response). Calculation: (20,000 / 1,000,000 * $0.25) + (2,000 / 1,000,000 * $1.00) = $0.005 + $0.002 = $0.007.
Input 10,000 tokens, output 800 tokens. Calculation: (10,000 / 1,000,000 * $0.25) + (800 / 1,000,000 * $1.00) = $0.0025 + $0.0008 = $0.0033.
Our pricing strategy is extremely simple: you only pay for the tokens you actually consume. Input tokens (context) are $0.25 per million, output tokens (generated content) are $1.00 per million. This structure reflects the difference in computational cost processed by the model. For uncensored scenarios requiring large context memory, input costs are relatively low, while the cost of generating content dominates. There are no hidden API call fees, and no distinction in billing by request. Whether it is a one-time long text generation or continuous roleplay dialogue, the rate remains consistent.
To support heavy users, we offer tiered top-up rewards. When the top-up amount reaches $50, an extra 5% balance is gifted; when it reaches $100, 10% is gifted. These bonuses are directly credited to your account balance and can be used to pay for subsequent token consumption. The prepaid model means you will never face a billing crisis due to unexpected high traffic. For creators needing a stable budget, a one-time top-up can lock in the current bonus ratio, and the balance is valid forever with no expiry date.
New users can register without binding a credit card. Each account receives $0.50 in free trial credit, valid for 7 days. This is enough to test the uncensored model's performance with adult content or sensitive topics, and verify the API's stability and latency. After the trial credit is used up or expires, the account automatically switches to prepaid status. This is the lowest-risk way to experience the uncensored llm api, allowing you to confirm if the model meets your content filtering standards before topping up.
To ensure service stability, each API key is limited to 300 requests per minute, with a single request body size not exceeding 8 MB. One account corresponds to one primary key; you can generate a new key at any time, and the old key will become invalid immediately. This design simplifies permission management. For most developers, 300 RPM is sufficient to support high-concurrency application scenarios. If the limit is exceeded, the API will return a 429 error. These limits ensure fair allocation of shared GPU resources and maintain high-quality output from the uncensored model.
We support cryptocurrency (USDT, USDC) top-ups, ensuring users worldwide can conveniently purchase balance. The minimum top-up amount is $10. The payment process is simple and direct, and the balance is available immediately upon arrival. We do not accept pay as you go post-payment; all services are deducted from the prepaid balance. This means your spending limit is always limited by your account balance, avoiding unexpected bills. For developers who prefer cryptocurrency, the payment process is completely anonymous and fast, suitable for privacy-conscious users.
No tiers: every key gets the full feature set and the same limits.
| Feature | Support |
|---|---|
| Tools / tool calls | Supported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages |
| Completion length | up to the rest of the 100,000-token window; max_tokens optional (no separate cap) |
| Context window | 100,000 tokens, input and output combined |
| Structured output | response_format: {"type": "json_object"} |
| Concurrency | 8 requests at the same time per key |
| Requests per minute | 300/min per key |
| Payment | USDT (TRC20) or USDC (Base), any whole amount from $10 to $500 |
| Trial credit | $0.50 of credit valid 7 days, no card needed · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up |
| Volume bonus | +5% on $50+, +10% on $100+ |
| Price | input $0.25 / 1M tokens, output $1.00 / 1M tokens |
| Subscription | no monthly fee; paid credit does not expire |
No. Whether from top-ups or bonus, once credited to your account, it is valid forever with no expiry date. Only the $0.50 new user trial credit has a 7-day validity.
Generating tokens requires more GPU compute to predict the next token one by one, while input tokens mainly involve embedding and attention calculations. Thus, the unit price of output tokens ($1.00/M) is higher than input tokens ($0.25/M).
Currently, Da Moxing api hosts only one fine-tuned uncensored large model. We do not offer multi-model routing or switching. If you need other specific models, you must find the corresponding API service.
No. After the trial credit is used up or expires, you just need to top up any amount (minimum $10) to continue using the service, without binding a credit card. Payment supports cryptocurrency (USDT, USDC).
Create an account, copy the key, modify the Base URL. Configuration is that simple.