> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gc.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Understanding the Context Window in GC AI
> How the GC AI context window works: token limits by model, the context usage indicator, on-demand document access, and tips for managing context.
When you use GC AI to analyze contracts or draft policies, you might wonder how it keeps track of everything you've uploaded or asked. That's where the context window comes in. The context window is the amount of information GC AI can "see" and work with at one time, like the working memory it uses to understand your documents and questions.
## What Is a Context Window?
The context window is the maximum amount of text (measured in tokens, which are bits of words or phrases) that GC AI can process in a single conversation. It includes your messages, the AI's responses, document content accessed during the conversation, and your Company Profile context.
The baseline context window is **200,000 tokens** (roughly 150,000 words). Some models support significantly larger windows. Claude Sonnet 4.6 and Gemini 3.1 Pro support up to 1,000,000 tokens.
## Context Usage Indicator
GC AI displays a context usage indicator in the chat composer footer. On desktop, hover the ring to see the percentage used; on touch devices, tap the ring. Click or tap opens the full breakdown, including token usage and guidance.
The indicator includes:
* **Percentage used** of the total context capacity
* **Token breakdown** showing how much of the window is in use
* **Color-coded warnings**: green when usage is comfortable, orange as it rises, and red when context is nearly full (about 80%+)
This helps you monitor usage and decide when to summarize, start a fresh chat, or keep going.
## How GC AI Frees Context Automatically
When a conversation gets long, GC AI can automatically summarize earlier parts of the chat so newer messages still fit. While that runs, you'll see **Summarizing earlier conversation...**. Afterward, a divider marks where compacted memory begins:
* Earlier messages stay visible in your chat history
* GC AI continues from the condensed summary plus recent messages
* You do not need to delete or restart the chat for this to happen
If response quality still dips after summarization, start a new chat for the next workstream (see tips below).
## Smart Document Access
GC AI uses an on-demand approach to document access rather than loading all document content into the context window upfront. When you attach documents or files, the AI uses specialized tools to:
* **Read specific sections** of a document as needed
* **Search across documents** for relevant passages using keyword matching
* **Query document content** using semantic search to find conceptually related information
This means you can work with many more documents than would fit in the context window at once. The AI accesses only the portions it needs for each response, keeping context usage efficient.
## Why It Matters for You
As an in-house counsel, you deal with complex legal work daily. Here's how the context window and smart document access help:
* **Large Documents:** GC AI can handle individual documents up to 50MB. The AI reads relevant sections on demand rather than consuming the entire context window.
* **Multiple Documents:** The on-demand approach lets you work with larger document sets than would otherwise fit in context.
* **Connected Analysis:** Ask about a clause on page 45, and GC AI can look up the definitions from page 45 using its document tools, keeping everything connected without filling the context window.
* **Tailored Advice:** Your Company Profile context is included to provide organization-aware responses.
## Model Fallback on Context Overflow
When your conversation approaches the context limit, GC AI can automatically fall back to a model with a larger context window to continue serving your request. This cross-provider fallback happens transparently. You won't need to take any action.
## Tips for Managing Context
When the indicator is climbing, you do not have to guess. **Ask GC AI how to best handle the situation based on the work at hand.** It can recommend the most practical next step for your specific chat, matter, and deliverable.
Other reliable approaches:
1. **Let automatic summarization run.** When GC AI summarizes earlier conversation, older messages remain visible while the AI works from condensed memory going forward.
2. **Start a new chat for a new workstream.** First ask for a handoff summary that covers final decisions, verified facts and sources, the current deliverable, standing instructions, and open questions. Paste or attach that into the new chat.
3. **Keep related chats in one [Project](/docs/chat/projects).** Project chats can reference sibling chats, and project instructions preserve formatting and matter-specific guidance.
4. **Use [chat history search](/docs/chat/agentic-chat-history-search)** to pull conclusions from an older conversation instead of copying an entire thread.
5. **Let the AI search your files.** Upload documents rather than pasting large blocks of text, and ask focused questions so GC AI reads only what it needs.
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.