Platform Guide

Conversation Context

Understand the context window, read the Conversation Context panel, and know why long chats start to "forget"

The short version: Every model can only hold a limited amount of content in view at once — that's its context window. The Conversation Context panel in Ask Sage Chat shows how much of that window your current conversation is using. This is not your Ask Sage token balance.
Table of Contents
  1. What Is a Context Window?
  2. The Conversation Context Panel
    1. Reading the Panel
    2. A Note on the Numbers
    3. Image and Video Models: the Prompt Size Panel
  3. Context Window vs. Ask Sage Tokens
  4. What Fills the Window
  5. What Happens When It Fills Up
  6. Managing Your Context Window
  7. Summary

What Is a Context Window?

The model's working memory

A context window is the total amount of content a model can hold in view at once, measured in tokens. Tokens can represent not just text but also images, audio, tool calls, and system instructions — anything the model processes. Think of the context window as the model's working memory for a single conversation: everything the model needs to answer your question has to fit inside it, and anything that falls outside it is no longer accessible to the model unless it's stored elsewhere and pulled back in.

Because models are stateless between turns, they don't remember your earlier messages on their own. A conversation appears to have memory only because the client resends the entire history — the system prompt, all prior turns, and your new message — with every turn. That's why long conversations grow slower and more expensive, and why they eventually hit the window's limit.

Tokens, briefly: For text, a token is roughly 3.7 English characters — a bit under a word, so a 1,000-word document lands somewhere near 1,300 tokens. Other content types are converted to tokens too, at rates that vary by model and media type. See Ask Sage Tokens for more.

The Conversation Context Panel

Where to find it

Ask Sage Chat shows a token badge in the bottom-right corner of the chat window. Click it to open the Conversation Context panel, which breaks down exactly how much of the model's context window your current conversation is consuming.

What the badge opens depends on the model you've selected. Chat models show Conversation Context, described below. Image and video generation models show a simpler Prompt Size panel instead, because they have no conversation to track.

Conversation Context panel showing model, window, reserve, budget, messages, and used tokens

The panel's own summary says it plainly: "How much of the model's context window this conversation is using. As you get close to 100% the oldest messages will be dropped."

Reading the Panel

What each field means

Field Example What it means
MODEL Auto → GPT-5.6 Luna The model the window belongs to. When you're on Auto, the arrow shows which model your request actually resolved to. Every number below follows that model, so they change if Auto routes elsewhere or you switch models mid-chat.
WINDOW 1,000,000 tok The resolved model's total context window — the hard ceiling on everything it can hold in view at once.
RESERVE 8,000 tok A fixed safety margin, held back on every model. USED is an estimate rather than an exact count, and the reserve is the cushion that absorbs the error — see A note on the numbers below.
BUDGET 992,000 tok WINDOW − RESERVE. This is what's actually available to your conversation, and it's the number the percentage is measured against.
MESSAGES 2 How many messages are currently being carried in context. Your prompt and the model's reply each count as one, so a single completed exchange shows 2. Text still sitting unsent in the prompt box isn't a message yet and doesn't count here.
USED 55 tok An estimate of how many tokens the conversation is consuming, calculated in your browser rather than by the model. Read it as an approximate gauge — see A note on the numbers below.
DRAFT +2,000 tok What the message you're currently typing will add. It appears only when there's unsent text in the prompt box, and it's already folded into USED — so you can see a long prompt's cost before you commit to sending it.
Percentage bar 0.0% USED as a share of BUDGET — not of WINDOW. As this approaches 100%, the oldest messages start dropping out.
Why the numbers change mid-chat: The window belongs to the model, not the conversation. Switching from a 200K-token model to a 1M-token model changes WINDOW and BUDGET instantly, and the same conversation will show a much smaller percentage. With Auto, the Allow switching toggle controls whether Auto can re-route between turns — see Model Selection.

A Note on the Numbers

Why USED is an estimate, and what RESERVE is for

There is no single, universal definition of a token. Every model family splits text into tokens slightly differently, so the same sentence genuinely costs a different number of tokens depending on which model is reading it.

Ask Sage has to know how big your conversation is before it sends anything, and it can't run every model's tokenizer in your browser to find out. So it uses one deliberately conservative approximation for all models. The figure you see is a working estimate of the conversation's size, not an exact accounting of everything in the request.

That's what RESERVE is for. It's a fixed 8,000-token margin, held back on every model, that covers the gap between the estimate and reality. Together they let Ask Sage manage the conversation on its own terms:

  • Estimate high — Assume the conversation is bigger than it probably is.
  • Hold back a reserve — Stop at BUDGET rather than at the model's true ceiling.
  • Trim before sending — When the conversation would exceed BUDGET, Ask Sage drops the oldest messages itself, on the way out.

The point of the margin is to keep that trimming decision on the Ask Sage side, where it's predictable. If the estimate ran low and an oversized request reached the model, the drop would happen further downstream and with less control over what gets cut.

What this means in practice: Treat the percentage as a gauge rather than a precise readout. It's the right number for spotting a conversation that's getting heavy, and the right prompt to start a fresh chat — just don't plan down to the last few percent, and give yourself room before a long or important task.

Image and Video Models: the Prompt Size Panel

A different panel for generated media

Select an image or video generation model and the same badge opens a different panel: Prompt Size. Media models don't hold a conversation — each request stands alone — so there's no history to track and nothing to drop. What's limited is the length of the prompt itself.

Prompt Size panel showing model, prompt limit, and prompt token count for an image generation model
Field Example What it means
MODEL Nano Banana 2 The media model your prompt will be sent to.
PROMPT LIMIT 32,768 tok The longest prompt this model accepts. This varies enormously between media models — Nano Banana 2 allows 32,768 tokens, while FLUX 2 Pro allows 1,024. Check the panel rather than assuming, especially when switching models.
PROMPT 11 tok How much of that limit your current prompt uses, updating live as you type.
Percentage bar 0.0% PROMPT as a share of PROMPT LIMIT. There's no reserve to subtract here.
The generated media doesn't count: As the panel says, the output is an image or video, not tokens — so it never counts against the prompt limit. Only the text you write does. This is the practical difference from a chat model, where the model's reply becomes history that eats into the next turn.
If you hit the limit: Tighten the prompt rather than starting over. On a tight-limit model, a long, discursive description can run out of room at a length that would be unremarkable in chat — the panel is the quickest way to see how close you are before you send.

Context Window vs. Ask Sage Tokens

Two different numbers, often confused

This is the single most common point of confusion on the platform. They are unrelated limits that happen to both be measured in tokens.

Context Window

A per-conversation capacity set by the model you're using.

Resets to zero on every new chat
Costs nothing on its own
Changes when you change models
Shown in the Conversation Context panel

Ask Sage Tokens

Your monthly plan allowance — the platform currency you spend to run prompts.

Shared across all your chats
Depletes as you use the platform
Resets on the 1st of each month
Shown in Settings → Tokens
How they interact: They're separate limits, but they pull on each other. Because the whole conversation is re-sent with every turn, a chat that's filled most of its context window sends a very large prompt each time you hit send — so it spends far more plan tokens per message than a fresh chat does. A long-running conversation gets more expensive the longer it runs, even when your latest message is one sentence.
Learn more: See Ask Sage Tokens for how inference and training tokens are billed, when they reset, and where to check your balance.

What Fills the Window

Everything shares one budget

It isn't just your messages. All of the following compete for the same space:

  • Your prompt — The question or instructions you type.
  • Chat history — Every prior turn in this conversation, yours and the model's, re-sent on each send.
  • Attachments — Files you attach to a prompt (up to 5 at a time). A handful of large PDFs can fill a small window on its own.
  • Dataset chunks — When a Dataset is attached, the retrieved passages are inserted into the prompt.
  • Persona & prompt templates — The instructions behind your selected Persona or template, sent with every turn. A long, detailed Persona takes up real room in the window.
  • Plugins & MCP tools — Enabled tool definitions occupy space before you ever call one, and each tool result adds more.
  • The model's response — Once written, it becomes part of the history carried into the next turn.
Rule of thumb: If you attach five 40-page PDFs to a single prompt, you'll fill the context window of most models. Either choose a large-context model or ingest the documents into a Dataset, where only the relevant chunks get retrieved.

What Happens When It Fills Up

Why the model "forgets"

As USED approaches BUDGET, Ask Sage starts dropping the oldest messages from what it sends, to make room for new ones. Nothing is deleted from your saved chat history — you can still scroll up and read the whole thing — but the dropped messages are no longer going to the model, so it can no longer see them.

This is the explanation behind the most common complaint about long chats:

  • The model contradicts an instruction you gave it 40 messages ago.
  • It asks for information you already provided.
  • It loses track of a document you attached early in the conversation.
  • Answers get vaguer or drift off-topic the longer the chat runs.

None of these mean the model is malfunctioning. They mean the earliest part of the conversation has aged out of the window. Checking the Conversation Context panel will usually confirm it — a high percentage is the tell.


Managing Your Context Window

Practical steps

  • Start a new chat when the topic changes — The single most effective habit. A fresh chat starts at 0% and isn't carrying irrelevant history that both costs tokens and subtly influences answers.
  • Switch to a larger-window model — Every model card in Browse Models lists its context window size. Open the model picker and click See All Models to compare.
  • Use Datasets instead of re-attaching files — Ingest a reference document once, then query it. Only the relevant chunks enter the window rather than the whole file, every time.
  • Turn off Plugins and MCP tools you aren't using — Their definitions consume window space on every send whether or not you call them.
  • Check the panel before a long task — If you're about to attach a large document to an already-long chat, open the panel first. Starting fresh is cheaper than discovering mid-task that half your setup got dropped.
Best Practice: Always start a new chat session when changing topics or contexts. Continuing a session with a different subject hinders the model's ability to generate accurate results. If a model starts misbehaving, starting a new chat session is also a good first debugging step — prior chat history may be influencing its responses.

Summary


Back to top

Copyright © 2026 Ask Sage Inc. All Rights Reserved. Ask Sage is a BigBear.ai company.