# LLM API glossary

> Tokens, context window, open weights, OpenAI-compatible, tool calling, streaming, quantization, median price, TRC-20: the LLM API and crypto terms explained.

- URL: https://llmwithcrypto.com/glossary/
- Last updated: 2026-10-23
- Publisher: LLMwithCrypto (https://llmwithcrypto.com)

The words you meet when you choose and pay for a language model API, explained in a sentence or two and tied back to how LLMwithCrypto works.

**Quick answer — What do the main LLM API terms mean?**

An **LLM API** sends text to a language model and returns its answer as data. You pay per **token**, a few characters of text, counted separately for **input** and **output**. **Open-weight** models can be run by anyone their licence allows. **LLMwithCrypto** serves 12 of them through the **OpenAI-compatible** chat format, priced per million tokens as of 23 October 2026. The 32 terms below explain the rest.

## Model terms

**LLM** — Large language model: a neural network trained on large amounts of text that predicts the next token, which lets it answer, summarize, translate or write code.

**Open-weight model** — A model whose trained parameters are published, so others can run it on their own hardware. What they may do with it depends on its licence.

**Closed model** — A model only its maker serves, such as GPT, Claude, Gemini or Grok. Access goes through the maker or partners it approves.

**Model licence** — The terms under which open weights are published: Apache 2.0 and MIT allow commercial serving; the Llama community licence adds conditions such as a use policy and the “Built with Llama” notice.

**Parameters** — The numbers inside a model. “120b” means about 120 billion; more parameters usually means more capable and more expensive to run.

**Mixture of experts (MoE)** — A design where only part of the model works on each token. In “Qwen3 235B A22B”, 235 billion parameters exist and about 22 billion are active per token.

**Reasoning model** — A model trained to work through a problem step by step before answering, such as DeepSeek R1. It often spends more output tokens per answer.

**Quantization** — Storing a model's numbers with fewer bits so it runs on less memory. It can lower quality slightly; hosts do not always say which precision they serve.

**Context window** — The maximum number of tokens a model can take in at once, prompt and answer together. Ours range from 128K to 1M tokens.

## API terms

**OpenAI-compatible API** — An API that accepts the same request and response format as OpenAI's, so its SDKs and the tools built on them work after changing the base URL.

**Base URL** — The address an SDK sends requests to. For LLMwithCrypto it is `https://llmwithcrypto.com/api/v1`.

**Chat completions** — The OpenAI request format with a list of messages (system, user, assistant) and a reply from the model. Our main endpoint is `https://llmwithcrypto.com/api/v1/chat/completions`.

**API key** — A secret string that identifies your account on each call, sent as a Bearer token. Keep it in an environment variable, never in code.

**Streaming** — Receiving the answer token by token as it is generated, through server-sent events, instead of waiting for the whole reply.

**Tool calling** — Letting the model ask your code to run a function, with arguments in JSON, and then use the result. Also called function calling.

**JSON output** — Asking the model to answer with valid JSON, set through `response_format` on models that support it.

**Rate limit** — The number of requests or tokens an account may send per minute. Ours is shown in the dashboard and can be raised on request.

**System prompt** — The first message of a conversation that sets the model's role and rules for the rest of it.

## Pricing terms

**Token** — The unit models read and write: a word or part of a word. In English, 1,000 tokens are roughly 750 words.

**Input and output tokens** — Input tokens are what you send, output tokens what the model writes. Output usually costs more per token.

**Price per 1M tokens** — How model APIs quote prices: the cost of one million input or output tokens. A call costs a fraction of it.

**Tokenizer** — The rule a model uses to cut text into tokens. The same text counts a different number of tokens on different models.

**Median host price** — The middle value of the prices that public hosts list for the same model. Our prices are 5% below it.

**Cached input** — A discount some hosts give when the start of a prompt repeats. We do not offer it yet.

**Credit pack** — Prepaid API credit bought at face value from your balance; it pays for any model and never expires.

## Payment terms

**KYC** — Know your customer: checks of identity documents or company papers before a service can be used. LLMwithCrypto does not do them.

**TRC-20** — The token standard of the Tron network. USDT on TRC-20 often costs the least to send for a small dollar amount.

**ERC-20** — The token standard of Ethereum, used for USDT and USDC there. Network fees can be high for small transfers.

**Network fee** — What the blockchain charges to process your transfer, paid by the sender to the network, not to us.

**Confirmation** — A block added after your transaction. We credit a top-up once its network has the confirmations it needs.

**Minimum top-up** — The smallest amount you can add to your balance: $25.

**Balance** — The dollar amount on your account after a top-up, from which you buy credit packs.

---

LLMwithCrypto: LLMwithCrypto is an OpenAI-compatible LLM API for open-weight models — DeepSeek V4 Pro, DeepSeek V4.1 Flash, DeepSeek R1, Qwen3.5 397B A17B, Qwen3 235B A22B Instruct, gpt-oss-120b, gpt-oss-20b, GLM-4.7, Llama 3.3 70B Instruct, Gemma 4 31B, Mistral Large 3, Mistral Small 4 — paid per token from a prepaid crypto balance, at 5% below the median price of the public hosts. No KYC: no ID, no selfie, no documents. Prompts and outputs are not stored.