Local log summarization
Processing a 10,000-token log file and generating a 1,000-token summary. Input cost: 0.0025. Output cost: 0.001. Total: $0.0035.
Stop paying for idle capacity. Our LLM API pricing is strictly pay-as-you-go with no minimum spend, so you only cover the tokens you actually consume.
No subscription. Prepaid credit never expires.
per 1M tokens
Processing a 10,000-token log file and generating a 1,000-token summary. Input cost: 0.0025. Output cost: 0.001. Total: $0.0035.
Generating 500 distinct 500-word articles from short prompts. Input: 25,000 tokens ($0.00625). Output: 250,000 tokens ($0.25). Total: $0.25625.
A user session with a 500-token prompt and a 2,000-token response. Input: $0.000125. Output: $0.002. Total: $0.002125.
cheap ai api operates on a transparent token basis rather than a complex tiered subscription. You pay $0.25 per million input tokens and $1.00 per million output tokens. This structure ensures that your costs scale exactly with your usage, making it easy to predict expenses for any volume of requests. There are no hidden fees for streaming or function calling, and the rates remain consistent regardless of the number of calls you make per minute.
To keep overhead minimal, we use a prepaid credit system. You can top up your balance starting at just $10 using crypto (USDT or USDC). We reward higher initial loads with bonus credits: adding $50 gives you a 5% bonus, while a $100 top-up provides a 10% bonus. These bonuses are applied instantly to your balance, effectively lowering your per-token cost for that period. There is no monthly fee to maintain your account.
Unused credit never expires. Whether you top up $10 or $1,000, those funds remain available until you consume them. This is ideal for indie developers with fluctuating traffic patterns. You do not need to worry about end-of-month resets or losing value on your account. You can add more credits at any time, and the balance simply accumulates, ensuring you always have funds ready when demand spikes.
Same price for every feature — function calling and JSON mode cost nothing extra.
| Spec | Value |
|---|---|
| Max output | 16,000 tokens max; 2,048 if max_tokens is not set |
| Context window | 100,000 tokens, input and output combined |
| Tools / tool calls | Yes — tools, tool_choice; replies carry tool_calls, also when streaming; send results back as role: tool |
| Structured output | response_format: {"type": "json_object"} |
| Parallel requests | 8 requests at the same time per key |
| Requests per minute | 300 requests per minute per key |
| Top-up | USDT (TRC20) or USDC (Base), any whole amount from $10 to $500 |
| Subscription | paid credit never expires, no subscription |
| Trial credit | $0.50 of credit valid 7 days, no card needed |
| Price | $0.25 per 1M input tokens · $1.00 per 1M output tokens |
| Bonus credit | +5% on $50+, +10% on $100+ |
No. You can sign up with just an email and password to receive $0.50 in trial credit valid for 7 days. Crypto (USDT or USDC) payment method is only required when you are ready to top up your balance for ongoing use.
Your account will stop processing new requests once the balance reaches zero. Existing requests that are already in progress will complete, but you cannot start new ones until you add more credits. There is no overage charge; you simply cannot spend more than what is in your prepaid balance.
There is no minimum spend per request or per month. You can make a single request for a few hundred tokens and be charged only for that small amount. The only minimum is the $10 threshold for topping up your account balance.
No, your prepaid credits do not expire. They remain in your account indefinitely until you use them to generate text. This allows you to top up during sales or when funds are available and use them whenever your project requires high-volume processing.
Create an account, copy the key, change the base URL. That is the whole setup.
https://api.cheapaiapis.com/v1