Unverified50% confidenceConceptExact time
A large model's context window refers to the upper limit on the total number of tokens it can "see" in a single conversation, including the system prompt, historical conversation, uploaded files, and the reply about to be generated; before each round of reply, Codex needs to send the entire project history back into the model, so the longer the conversation, the higher the usage, and when the limit is reached it will truncate or report an error.
1
Sources
50%
Confidence
Long-term
Relevance
10/25/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedLong conversations package and resend the entire context history to the model, which is counted toward the token usage of each request; the longer the conversation, the more tokens a single request consumes.79% similarUnverifiedThe model has no memory between messages; each time a message is sent, the application resends the entire conversation (system instructions, conversation history, and the new message) to the model, and this package is called the context window, which has a size limit.79% similarUnverifiedContext is all the information the model can see when generating the current reply (including system prompts, historical conversation, uploaded files, etc.), it is measured in tokens and has an upper limit, and when approaching the limit the earlier content will be discarded or needs to be compressed77% similarVerifiedThe context window determines how much content the model can remember within a single conversation.76% similarVerifiedThe context window mechanism causes models in multi-turn conversations to feed the entire conversation history into the context, causing token consumption to grow rapidly as the conversation lengthens.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1095006API
curl https://kongchang.com/api/v1/knowledge/claims/1095006MCP
get_claim(id=1095006)