Number of context windows for GPT4V

What is the context window size of gpt-4-vision-preview? Only 4096 token? Still greater than 4096? Is there any documentation?

Models - OpenAI API


GPT-4 with the ability to understand images, in addition to all other GPT-4 Turbo capabilities. Returns a maximum of 4,096 output tokens. This is a preview model version and not suited yet for production traffic. Learn more.

Context Window: 128,000 tokens

The input limit (aka context window) is 128k tokens. The Output is limited to 4k tokens

Thank you very much for your answer. :100: