Context Window
The maximum span of tokens an LLM can consider in a single forward pass. Frontier models in 2026 support 1M-2M token contexts, but effective context (measurable retrieval accuracy across the window) usually lags nominal capacity.
Related terms
- Retrieval-Augmented Generation (RAG)
A pattern where an LLM answers a query by first retrieving relevant documents from an external corpus (typically via a vector database or hybrid search) and injecting them into the prompt as grounding context. RAG addresses freshness and factual grounding without model retraining.
- Reasoning Model
A class of LLMs (OpenAI o-series, Claude with extended thinking, DeepSeek-R1) trained to spend significant inference-time compute on internal reasoning before producing the final answer. Substantially better on math, coding, and multi-step problems at the cost of higher latency and token consumption.
Related on this site
Where this fits
Context Window is part of the AI Fundamentals vocabulary used in the Generative AI Maturity Framework. See the full glossary for the complete set of 149 defined terms, or take the free maturity assessment to see where your organisation stands.