Frequently asked questions

Only open-weight models whose licences allow serving them as an API: DeepSeek, Qwen, gpt-oss, Mistral, Llama, Gemma and others listed on the models page. We run them on GPUs we rent and operate. The models page lists all 12 with their API ids, licences and prices.

We do not sell access to GPT, Claude, Gemini or Grok: their makers forbid reselling API access without their approval, and we do not have it. The resale rules dataset quotes each provider.

The API speaks the OpenAI chat completions format: point the OpenAI SDK, LangChain or any OpenAI-compatible tool at our base URL with your key, and change the model name. See what is compatible.

Streaming works on every model; tool calling and JSON output follow what each model itself supports. Guides: streaming and tool calling.

Change the model field. One key calls every model, and GET https://llmwithcrypto.com/api/v1/models lists them.

Each model costs 5% less than the median price of the public hosts that list it, for input and output tokens, read on 2026-10-23. The price index shows every host price behind each median.

You pay per token from your balance: input and output tokens are counted by the model’s own tokenizer and charged at that model’s price per 1M tokens. A call that ends in an error costs nothing.

No. Credit has no expiry date: what you do not spend this month is still there next year.

There is no free tier: the smallest credit pack is the way to try it, and unspent credit never expires.

A credit pack bought in the last 72 hours goes back to your balance if less than 20% of it was spent. If the API does not work for you and support cannot fix it within 24 hours, the unspent credit goes back to your balance. Top-ups stay on the balance and are not paid out unless the law requires it; whatever you added only to reach the minimum top-up comes back on request within 30 days, in USDT or USDC, as long as it is unspent. Details in the refund policy.

BTC, USDT, USDC, ETH, SOL, LTC, from a $25 top-up. The crypto payments page explains each network.

No. Sign in with an account number; an email address is optional.

Your account number is how you sign in, so store it carefully. With an optional email on file you can recover it; with no email, a lost number is gone for good.

Once your crypto top-up is confirmed and a credit pack is bought, your API key is waiting in the dashboard.

No. We do not store your prompts or the model’s answers: once a response is sent, its text is gone. Each call leaves one log line with the time, the account, the model and the token counts, deleted after 30 days.

No. We never train or fine-tune any model on your prompts or outputs.

Each call leaves one log line: the time, the account, the model and the input and output token counts. Lines are deleted after 30 days. Prompts and answers are not kept. Account number, orders, top-ups and balance stay while the account exists, then only as long as accounting law asks. Authorities receive records only when a law compels us.

Child sexual abuse material, malware and attacks on systems, weapons capable of mass casualties, spam and fraud, harassment and threats, deceiving people that they talk to a human, and anything a model’s own licence or use policy forbids or that is illegal where you or we operate. The acceptable use policy has the details.

Not available to people or companies in Iran, North Korea, Cuba, Syria, Russia, Belarus or the occupied regions of Ukraine, because of sanctions.

Yes. Every account has a per-minute request and token limit, shown in the dashboard; ask support and it can be raised.

Yes. Each model keeps its own licence and use policy (for example Meta’s Llama Acceptable Use Policy and the “Built with Llama” notice); using a model through us means accepting them.