Context Window
A context window is the maximum amount of text (measured in tokens) that an AI model can process in a single request. It includes both the input (your message plus conversation history) and the output (the model's response).
How It Works
Context window sizes vary dramatically between models. GPT supports 128K tokens. Claude supports 200K tokens. Some models support over 1 million tokens. A larger context window means the model can consider more information when generating a response, which is critical for long documents, complex codebases, and extended conversations. However, larger context windows typically cost more per request.
Context Window in Chapeta
Chapeta shows real-time prompt token counts from the API, so you can see exactly how much context you are using. When switching between models with different context sizes, the indicator adapts to the new model's limit. The context window is especially important when using file attachments, as documents and code files consume context tokens.
Related
More Terms
OpenRouter
OpenRouter is a unified API gateway that provides access to hundreds of AI models from different providers through a single API endpoint.
BYOK (Bring Your Own Key)
BYOK stands for Bring Your Own Key.
LLM (Large Language Model)
A Large Language Model (LLM) is an AI system trained on massive text datasets that can understand and generate human language.
AI Agent
An AI agent is an AI system that can take actions in the real world, not just generate text.
API Key
An API key is a unique string of characters that authenticates your identity when making requests to a web API.
Prompt Engineering
Prompt engineering is the practice of crafting input text (prompts) to get the best possible output from AI models.
Token
A token is the basic unit of text that AI models process.
Fine-Tuning
Fine-tuning is the process of further training a pre-trained AI model on a specific dataset to specialize it for a particular task or domain.