GPT-4 is an advanced multimodal model that not only takes text or image inputs but also outputs text. Its broad general knowledge and powerful reasoning capabilities enable it to solve more complex problems with greater accuracy and efficiency than ever before. Moreover, GPT-4 has been optimized for chatbots but it is also effective for traditional completion tasks.​
| MODEL | DESCRIPTION | CONTEXT WINDOW | TRAINING DATA |
|---|---|---|---|
gpt-4-1106-preview
GPT-4 model with improved instruction following, JSON mode, reproducible outputs, and more. The model has been optimized for maximum output of 4096 tokens and utilizes parallel function calling to speed up response times. This model is not yet suitable for production traffic, but it is a preview model that can be used for experimenting and testing.
128,000 tokens
Up to Apr 2023
gpt-4-vision-preview
Ability to understand images, in addition to all other capabilties. Returns a maximum of 4,096 output tokens. This is a preview model version and not suited yet for production traffic.
128,000 tokens
Up to Apr 2023
gpt-4
Currently points to gpt-4-0613.
8,192 tokens
Up to Sep 2021
gpt-4-32k
Currently points to gpt-4-32k-0613.
32,768 tokens
Up to Sep 2021
gpt-4-0613
Snapshot of gpt-4 from June 13th 2023 with improved function calling support.
8,192 tokens
Up to Sep 2021
gpt-4-32k-0613
Snapshot of gpt-4-32k from June 13th 2023 with improved function calling support.
32,768 tokens
Up to Sep 2021
gpt-4-0314 Legacy
Snapshot of gpt-4 from March 14th 2023 with function calling support.
8,192 tokens
Up to Sep 2021
gpt-4-32k-0314 Legacy
Snapshot of gpt-4-32k from March 14th 2023 with function calling support.
32,768 tokens
Up to Sep 2021