What Most Developers Still Don’t Know about OpenAI API

OpenAI's API offers tools beyond simple text generation, including web search, code interpreter, vision, function calling, and JSON mode, which most developers never use. According to a conversation with a junior AI engineer, many are unaware of these capabilities, which allow GPT-5 to search the web, execute Python, analyze images, and interact with backends. The article highlights the gap between 'GPT writes text' and 'GPT can act' as a key insight for developers.

Member-only story What Most Developers Still Don’t Know about OpenAI API A practical breakdown of OpenAI API tool use: web search, code interpreter, vision, function calling, and JSON mode, the features most AI engineers never touch. Most developers think they know the OpenAI API. You send a prompt, the model replies, and that’s it. A conversation I had with a junior AI engineer a few weeks ago reminded me how common this misconception is. He was surprised to learn that the API can search the web, read documents, execute Python, generate files, analyze images, and interact with your own backend… That’s not a knock on him. Most developers are taught the API the same way: prompt in, text out, end of story. Nobody tells them GPT-5 and the models around it are wired up to a full toolbox that almost nobody opens. So I decided to write this up and share it with everyone, because the gap between “GPT writes text” and “GPT can act” is one extra argument in most cases. Web Search Real-Time Research, No Search API Required Language models only know what they were trained on, which is exactly why they get confidently wrong about anything recent. The web search tool…