Glossary
Short, plain-English definitions of the terms behind free LLM and AI API offers. Each one is a standalone answer you can quote.
- Context window
- A context window is the maximum number of tokens a model can consider at once — the combined size of your prompt and the model's response — ranging from a few thousand to over a million tokens depending on the model.
- Free tier
- A free tier is an ongoing, no-cost allowance that lets you use an API or service within set usage limits (such as requests per minute or per day) without paying and often without a credit card.
- Inference
- Inference is the act of running a trained model to produce an output — turning your prompt into a response — and it is the usage that API free tiers, trial credits, and per-token pricing pay for.
- Rate limit
- A rate limit is the cap a provider places on how often you can call an API — commonly expressed as requests per minute (RPM), requests per day (RPD), or tokens per minute (TPM) — and free tiers usually have the tightest limits.
- Startup credits
- Startup credits are larger blocks of free API or cloud usage granted to eligible early-stage companies through a provider's startup program, typically requiring an application and proof of eligibility.
- Token
- A token is the unit of text an LLM processes — roughly 4 characters or about three-quarters of a word in English — and API usage and free allowances are usually measured and priced per token.
- Trial credit
- A trial credit is a one-off, time-limited amount of free usage (often expressed in dollars or tokens) given to new accounts to try a paid service, after which you pay as you go.