Glossary

AI subscription terms, explained

The jargon behind the scores, in plain English.

Context windowHow much text (in tokens) a model can consider at once. Bigger windows handle longer documents and chats. ~750 words ≈ 1,000 tokens.
TokenThe unit models read and write – roughly a short word or word-piece. Limits and context are measured in tokens.
Frontier modelThe newest, most capable model a lab offers. Paid plans usually unlock it; free tiers may not.
Reasoning modelA model tuned to think step-by-step for harder maths, logic and coding tasks.
Agentic / tool useWhen the AI can take multi-step actions and call tools (search, code, browse) to complete a task, not just answer.
MultimodalUnderstands more than text – images, audio, sometimes video.
RAGRetrieval-augmented generation: the AI looks up sources first, then answers – the basis of cited, research-style answers.
HallucinationWhen a model states something false confidently. Always verify important facts.
Aggregator / all-in-oneA subscription that bundles several models behind one interface so you can compare or switch.
Token limit / rate limitCaps on how much you can use per period on a given plan.
SSO / SCIMSingle sign-on and user provisioning – important for teams and enterprises.
Zero-data-retentionAn option where prompts aren't stored after processing – used in sensitive/enterprise settings.