PentestLLM is a prepaid LLM API. You add credit in the console, every request draws on it at its model’s per-token price, and when the credit runs out the API answers 402 Payment Required until you top up. Below: each part of that, with the exact response you will see, the requests that cost nothing, and what is kept. Prices are read from the live catalog on November 18, 2026, and every model’s daily result is on the daily check.
Top up from $10, by card, WeChat Pay or Alipay
Top-ups happen in the console, from $10 to $10,000 at a time. The top-up window takes a card through our payment processor’s form, or WeChat Pay or Alipay by a QR code you scan with either wallet. Whichever you choose, the credit lands on the same balance, and your first payment also creates your first key.
Larger top-ups add bonus credit: +5% from $200, +10% from $500, +15% from $1,000. The bonus is credit, not money, so a refunded or disputed payment takes its bonus back with it. WeChat Pay and Alipay top-ups earn the same bonus as card top-ups.
One more way to pay. Gift cards: prepaid credit codes bought in packs in the console, for a class, a hackathon or a giveaway, redeemed on the billing page.
Each top-up also holds the per-token prices you were paying for 30 days. Inside that window a model’s price can drop for you but not rise; a rise reaches you at most 30 days later. A model added after your top-up bills at its current price.
How a request is priced
Every chat model has an input and an output price per million tokens, and some have a lower price for cached input. A request costs its tokens times those prices, counted to the token, with no per-request fee on top. The price index has every row; these five are read from the same catalog:
| GLM-5.3 Flash Uncensored | Uncensored | $0.1053 | $0.3685 |
| Cydonia 24B v4.3 | Roleplay | $0.484 | $0.60 |
| DeepSeek V4 Pro Uncensored | Uncensored | $0.97 | $1.94 |
Prompt tokens a host counts beyond what your request could hold are left out of the charge and out of your token counts. A non-streamed answer carries its settled charge in the x-uplink-charge header; a streamed one ends with its usage block. The console’s usage log lists every request with its id, tokens and charge, and the billing page has a CSV of every request for each month.
When the prepaid LLM API balance hits zero
A request goes ahead only when the balance covers its estimated cost: the prompt, plus the most output it may return. When it cannot, the API answers 402 at once, sends nothing to a model and charges nothing. The body is the OpenAI error shape:
HTTP/1.1 402 Payment Requiredcontent-type: application/jsonx-uplink-request-id: ul_…x-uplink-error: insufficient_balancex-uplink-topup-url: https://app.pentestllm.ai/console/billing?topup=open { "error": { "message": "The prepaid balance does not cover this request. Top up at https://app.pentestllm.ai/console/billing?topup=open to continue.", "type": "insufficient_quota", "param": null, "code": "insufficient_balance" }}Retrying does not help; a top-up does, and the link in the message opens the top-up form. Without max_tokens, the estimate assumes 16,384 output tokens. Setting max_tokens lets a small balance still cover a short answer.
Two other 402 codes come from limits rather than the balance:
monthly_limit_reached: the key hit the monthly spend limit set on it in the console. Raise the limit or wait for the next month.spend_cap_reached: a new account may spend up to $10 before its first payment settles.
You hear before you hit zero. An account that made requests in the last 7 days and has no auto top-up gets one email when its balance drops below a day of its recent spend (or $1, whichever is higher), and one more when it runs out. Each top-up re-arms both.
Requests that cost nothing
- Failed requests. A request the host does not answer, or answers with an error, is not charged.
- Refused answers. When the model itself refuses, by its own refusal signal (a
refusalfield, or a finish reason ofrefusalorcontent_filter), the answer is free. The gateway never guesses a refusal from the wording. - Answers that miss the format you asked for. A non-streamed request that asks for JSON (
response_formatwithjson_objectorjson_schema, per the OpenAI structured outputs guide, or the headerx-uplink-require: json) pays only for an answer that parses and matches the schema. A miss is retried once, and the missed answer is free. - Refused image and video prompts. A prompt the gateway refuses under the acceptable use policy is refused before it is priced. A generation that fails after the host accepted it is refunded.
Limits on the guarantees
Refused and missed answers are free up to $5 per account per UTC day; past that they bill as usual, so neither guarantee can be farmed. An answer cut off by your own max_tokens is billed, because that limit is your choice. A refunded non-streamed answer carries the header x-uplink-refund with the reason.
Auto top-up
Nothing charges a card except a top-up or usage plan you buy, auto top-up, and the renewal of a plan bought by card. Auto top-up refills the balance from a card saved with our payment processor: when the balance drops under the threshold, the set amount is charged and credited. The threshold runs from $5 to $500 and the amount from $10 to $500. It tries at most once an hour and 5 times a UTC day, and 3 declines in a row switch it off with one email.
Auto top-up can also switch on by itself. If a card is already saved with our payment processor when your first card top-up arrives, it turns on with a $5 threshold and the amount of that top-up (from $10 to $500), and the receipt says so. The console’s billing page saves a card, shows the setting, changes it and switches it off.
Expiry, refunds and disputes
Credit has no expiry date. Nothing in the ledger removes credit for age or inactivity: the balance goes down for requests you make and for payments that are reversed. A month with no requests costs nothing.
Top-ups are not refundable, as the terms and the refund policy say. A payment that is refunded, or disputed with your card issuer, is reversed in the ledger, and keys may be paused until the balance is positive. The unused balance of an account closed for breaking the terms or the acceptable use policy is not refunded.
What is kept, and for how long
Each request leaves one usage record: the request id, the model, token counts, the charge and how long it took. Next to it sit SHA-256 fingerprints of the request and the response, never the text. Prompts and completions pass through and are not written anywhere, unless you turn on replay for a key, which keeps that key’s request bodies for 7 days.
From checkout we keep the email and the amount paid, as our payment processor reports them; card numbers stay with the processor. Usage records and ledger entries are kept as accounting records, also after an account closes. The hosts that run the models receive the request and the response for the calls they serve. The privacy page is the full list.
Questions
No. Credit has no expiry date, and nothing removes it for age or inactivity: the balance goes down for requests you make and for payments that are reversed. A month with no requests costs nothing.
Yes. A request goes ahead only when the balance covers its estimated cost; otherwise the API answers 402 with the code insufficient_balance and charges nothing. A card is charged only by a top-up or usage plan you buy, by auto top-up, or by the renewal of a plan bought by card, and the console's billing page shows whether each is on.
A request the host fails is not charged. An answer the model refuses by its own refusal signal is free, as is a non-streamed JSON answer that misses the schema you asked for, up to $5 per account per UTC day. An answer cut off by your own max_tokens is billed.
No subscription is required. You top up from $10 and each request settles per token.
Yes. The console's top-up window has a WeChat Pay button beside Pay by card: scan the QR code with WeChat and the credit lands on the balance once the payment confirms. It covers one-time top-ups from $10, priced in USD, with the same bonus credit; usage plans are card only.
A declined attempt charges nothing and leaves no pending top-up. The card form the window opens depends on your country: in mainland China and the other countries our first card processor does not serve, the window switches to a second card form on its own, so open the top-up window again and let it load fully before entering the card. If the card is declined there too, choose WeChat Pay or Alipay in the same window, pay the same amount in crypto (stablecoins and the main coins are accepted, the credit lands in minutes and earns the same bonus), or use another card. Write to hello@pentestllm.ai with the time of the attempt if none of these works; never send card numbers by email.
被拒绝的尝试不会扣款,也不会留下待处理的充值。充值窗口会按所在国家选择银行卡表单:在中国大陆以及第一家卡支付处理商不服务的国家,窗口会自动切换到第二家卡支付表单,请重新打开充值窗口,等待表单完全加载后再输入卡号。若仍被拒绝,可以在同一窗口改用微信支付或支付宝,或用加密货币支付同样的金额(支持 USDT 等稳定币和主流币种,数分钟内到账,奖励额度相同),或换一张卡。这些方式都不行时,请把尝试的时间发到 hello@pentestllm.ai,不要在邮件里发送卡号。
Chat requests are not filtered for topic; the models answer the way their builds answer. Image and video prompts that describe a minor are refused before they are priced. The acceptable use policy lists what is never allowed. See the acceptable use policy.
No, unless you turn on replay for a key, which keeps that key's request bodies for 7 days. Each request leaves a usage record and SHA-256 fingerprints of the request and response, never the text. See the privacy page.
Every model above is on the uncensored model list with its live price per million tokens. Per-token pricing sets the whole catalog side by side, and the family directory groups the builds by base model.