Glossary
Context window
The maximum text a model can consider in one request: prompt, documents, conversation and answer combined.
Measured in tokens. Flagship models in 2026 advertise around one million tokens. Everything in the window is billed as input on each request, and accuracy on very long inputs is lower than on short ones.
Related terms
Active parametersAPIAttentionLarge language model (LLM)Latency
Get the brief in your inbox
One email every morning: the stories that mattered in AI, each with a one-line "why it matters" for your role. Free, no ads, unsubscribe any time.
Published daily by AI Briefing. We never share your address.