# Does 'Composer' retain 'Composer Chat' history? **URL:** \ **Category:** Help\ **Created:** [July 17, 2024, 6:29am UTC](https://forum.cursor.com/t/does-composer-retain-composer-chat-history/6508 "2024-07-17T06:29:46Z")\ **Posts on this page:** 1\ **Showing post:** 15
**Author:** ![litecode](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/litecode/32/2966_2.png) [@litecode](https://forum.cursor.com/u/litecode)\ **Post date:** [August 18, 2024, 10:07am UTC](https://forum.cursor.com/t/does-composer-retain-composer-chat-history/6508/15 "2024-08-18T10:07:49Z")
> [@leoing](#): > > That’s a mistake, only sonnet 3.5 is capable enough for composer. Hi @leoing , Out of interest, why do you say that? Do you mean in terms of the context-window size or something else? And why would there be different considerations for model selection in Composer (`Ctrl` + `I`) as opposed to model selection in `Ctrl` + `L`? There is some uncertainty around context-window sizes in Cursor which I captured in the post below. But it seems, when used in Cursor, `gpt-4o` has a 20k window, whereas `claude-3.5-sonnet` has a 10k window? > [@What is the context size for gpt 4o mini?](https://forum.cursor.com/t/what-is-the-context-size-for-gpt-4o-mini/7688/2): > > I would be interested to know: 01) The actual context size of the LLMs available, ie: Normal Chat: cursor-small gpt-3.5 gpt-4o-mini gpt-4o claude-3.5-sonnet Long Context Chat: gpt-4o-128k gemini-1.5-flash-500k claude-3-haiku-200k claude-3.5-sonnet-200k 02) The context size of the LLMs when used within Cursor There seems to be a bit of uncertainty about this: And I saw you recently asked a question about the general topic as well: I am a bit confused why there would … --- _[View the full topic](https://forum.cursor.com/t/does-composer-retain-composer-chat-history/6508)._