The API for uncensored AI models
Transparent pricing for KiApi
Use KiApi without monthly fixed costs: top up credit and pay only for actual token usage. This pay-as-you go structure guarantees maximum transparency and predictability for your AI integrations.
No subscription. Prepaid credit never expires.
- per 1M input tokens
- $0.25
- Output tokens / 1M
- $1.00
- Context window
- 100,000
- Free trial credit
- $0.50
- Requests per minute
- 300
Cost calculator
Example calculations
Short, fast response for a chatbot
A typical request for a short answer consumes about 500 input tokens and 200 output tokens. The cost is calculated as follows: (500 / 1,000,000) * $0.25 + (200 / 1,000,000) * $1.00 = $0.000125 + $0.000200 = $0.000325 per request.
Processing a longer document
Analyzing a text with 30,000 input tokens and 2,000 output tokens costs: (30,000 / 1,000,000) * $0.25 + (2,000 / 1,000,000) * $1.00 = $0.00750 + $0.00200 = $0.00950 for this single run.
High-volume batch job with 1 million tokens
For a batch job with 600,000 input tokens and 400,000 output tokens, the result is: (600,000 / 1,000,000) * $0.25 + (400,000 / 1,000,000) * $1.00 = $0.15 + $0.40 = $0.55 total cost.
The pay-as-you go model of KiApi
KiApi completely eliminates monthly base fees or reserved quotas. You top up any amount and use the uncensored LLM exactly as much as you need. This is ideal for developers whose traffic fluctuates or who want to start small. Once the balance is depleted, output stops; no hidden fees are incurred because your request is only processed if credit is available. This structure eliminates the risk of paying for unused capacity and offers full control over your spending.
Balance top up and bonus
The minimum top up is $10, payment is supported via crypto (USDT or USDC). For regular users, we offer automatic bonuses: starting from a top up of $50, you receive 5% extra credit; from $100, it is 10%. These bonuses are credited directly to your account and significantly extend the usage duration of your capital. This maximizes your ROI when integrating KiApi into your applications without changing the base price per token.
Validity and planning security
A key advantage of our model: the topped-up balance remains permanently on your account and never expires. There are no deadlines by which you must consume your tokens. You can regenerate your API keys as you wish without losing the balance. This long-term validity makes KiApi the perfect choice for projects that perform continuous but irregular text generation over months or years, as you never have to worry about expiring contracts.
Plan details
One price list, one set of limits, all features on every key.
| Parameter | Details |
|---|---|
| JSON mode | response_format: {"type": "json_object"} |
| Function calling | Supported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages |
| Context window | 100,000 tokens, input and output combined |
| Max output | prompt + completion fit within 100,000 tokens; max_tokens optional, no separate output cap |
| Rate limit | 300/min per key |
| Concurrency | up to 8 in parallel per key |
| Token prices | $0.25 per 1M input tokens · $1.00 per 1M output tokens |
| Credit expiry | paid credit never expires, no subscription |
| Volume bonus | +5% from $50, +10% from $100 |
| Payment | USDT (TRC20) or USDC (Base), any whole amount from $10 to $500 |
| Free trial | $0.50 for 7 days, no card · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up |
Frequently asked questions
How do I get the free trial credit for KiApi?
Every new account automatically receives $0.50 in free trial credit after registering with email and password. This credit is valid for 7 days and requires no credit card to activate. The credit is available once per person and is designed to let you test the API integration and response quality without commitment.
Are there fees for connections or latency?
No, billing is strictly per token. There are no additional costs for the number of requests, connection quality, or latency. You pay exactly for the amount of input and output tokens your model processes. This applies to both standard requests and streaming connections via SSE.
What happens when my balance runs out?
Once the balance is depleted, your requests will no longer be processed until you top up. No debt is incurred since you can never spend more than what is on your account. You can add new credit at any time via your dashboard or the API and continue working immediately.
Can I revoke my API keys without losing balance?
Yes, you can regenerate your API key at any time. The old key becomes invalid, but the remaining balance remains fully on your account. This is useful if you use the key in different environments and want to swap it quickly in case of security concerns without fearing financial loss.
Your key is just one click away
Create account, copy key, adjust base URL. That’s it.
