# What is the context window of gpt 4 **URL:** \ **Category:** API\ **Tags:** gpt-4, chatgpt, api\ **Created:** [March 29, 2024, 6:25am UTC](https://community.openai.com/t/what-is-the-context-window-of-gpt-4/701256 "2024-03-29T06:25:33Z")\ **Posts on this page:** 5\ **Page:** 1
**Author:** ![sardarm2019](https://avatars.discourse-cdn.com/v4/letter/s/b9bd4f/32.png) [@sardarm2019](https://community.openai.com/u/sardarm2019)\ **Post date:** [March 29, 2024, 6:25am UTC](https://community.openai.com/t/what-is-the-context-window-of-gpt-4/701256/1 "2024-03-29T06:25:33Z")
What is the context window of GPT 4 turbo. In the below image what will be context window of first gpt. Any official source ![gpt](https://us1.discourse-cdn.com/openai1/original/4X/7/a/0/7a0779edb28129ccb840edb701421e1d527088e7.png) ---
**Author:** ![Innovatix](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/innovatix/32/193579_2.png) [@Innovatix](https://community.openai.com/u/Innovatix)\ **Post date:** [March 29, 2024, 7:12am UTC](https://community.openai.com/t/what-is-the-context-window-of-gpt-4/701256/2 "2024-03-29T07:12:50Z")
You can check this information in the OpenAI documentation. GPT-4 also known as GPT-4-0613 (GPT 4 Points GPT-4-0613), has a context window of **8,192 tokens** , while GPT-4 turbo (Points GPT-4-0125-preview) has a context window of **128,000 tokens**. Quick Link 👇 [https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) ---
**Author:** ![NotFenixio](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/notfenixio/32/205000_2.png) [@NotFenixio](https://community.openai.com/u/NotFenixio)\ **Post date:** [March 29, 2024, 7:12am UTC](https://community.openai.com/t/what-is-the-context-window-of-gpt-4/701256/3 "2024-03-29T07:12:52Z")
GPT-4 Turbo has a context window of 128k and a maximum response size of 4096 tokens. Source: [https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) Ninja’d! ---
**Author:** ![obadarneh99](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/obadarneh99/32/148406_2.png) [@obadarneh99](https://community.openai.com/u/obadarneh99)\ **Post date:** [June 12, 2024, 4:52pm UTC](https://community.openai.com/t/what-is-the-context-window-of-gpt-4/701256/4 "2024-06-12T16:52:19Z")
> [@Innovatix](#): > > You can check this information in the OpenAI documentation. GPT-4 also known as GPT-4-0613 (GPT 4 Points GPT-4-0613), has a context window of **8,192 tokens** , while GPT-4 turbo (Points GPT-4-0125-preview) has a context window of **128,000 tokens** Dears, I did not get the point regarding the difference between context windows and the maximum response. I am using gpt4-o and I can get a response which is 4096 maximam; what is the value of 128K conext window; how to utilize it ---
**Author:** ![NotFenixio](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/notfenixio/32/205000_2.png) [@NotFenixio](https://community.openai.com/u/NotFenixio)\ **Post date:** [June 12, 2024, 4:55pm UTC](https://community.openai.com/t/what-is-the-context-window-of-gpt-4/701256/5 "2024-06-12T16:55:54Z")
Context window means the maximum amount of tokens a model can be fed, while the maximum response size means the maximum tokens a model can output. So, if you have a context window of 128k, you could input several documents or even small books and get your model to output a max of 4096.