Context window
How much text an LLM can see at once — including your prompt and its own reply. If your client chat history exceeds this limit, the model will lose track of earlier context, potentially leading to a loss of decision survivability.
The total capacity of tokens a model can process in a single interaction. This includes the system prompt, the conversation history, and the current input. Once exceeded, the model "forgets" the earliest parts of the conversation.
The total capacity of tokens a model can process in a single interaction. This includes the system prompt, the conversation history, and the current input. Once exceeded, the model "forgets" the earliest parts of the conversation.
evolution
- 2017-06 · historyTransformer Architecture
The 'Attention Is All You Need' paper introduced the self-attention mechanism, establishing the fixed-length token limit inherent to Transformer models.
- 2020-05 · historyGPT-3 Release
OpenAI launched GPT-3 with a 2,048-token context window, setting the standard for large-scale generative language models of that era.
- 2023-03 · historyGPT-4 Expansion
OpenAI introduced GPT-4 with an 8k context window, later expanded to 32k, significantly increasing the amount of information models could process simultaneously.
- 2023-06 · historyContext Window Scaling
Anthropic released Claude with a 100k token context window, shifting the industry focus toward massive document analysis capabilities.
- 2024-02 · historyGemini 1.5 Pro
Google introduced a 1-million-token context window, enabling the processing of vast datasets, entire codebases, or long-form video in a single prompt.