AI Wiki · Mediocre Security
Concept

Context window

How much text, in tokens, a model can see at once in a single request; 1M tokens became common in 2026.

The context window is the maximum number of tokens a model can consider at once: prompt, documents, conversation and its own output. It grew from a few thousand tokens in 2022 to 1M tokens as a common 2026 figure (DeepSeek V4, GLM-5.2, Kimi K3.1, Muse Spark Open, GPT-6.1 Terra at 1.05M). Large windows reduce but don’t eliminate the need for retrieval, and they enlarge the surface for prompt injection, since more untrusted text reaches the model.

Connections

Context window and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →

What links here

Model family Gemini

Concept Retrieval-augmented generation (RAG) · Token