OpenAI updates its new Responses API rapidly with MCP support, GPT-4o native image gen, and more enterprise features
1 min read
Summary
OpenAI is rolling out updates to its Responses API, launched in March 2025, designed to help developers and enterprises build AI-driven applications more easily.
The upgraded API now features support for remote Model Context Protocol (MCP) servers, enabling developers to connect OpenAI’s models to third-party services using just a few lines of code, thus allowing the creation of agents that can take actions and interact with systems consumers already use.
Native image gen and Code Interpreter tools have also been incorporated, enabling developers to build apps that produce and edit images in response to user input, and allowing models to handle data analysis, complex math, and logic-based tasks.
File search functionality has been improved, with the ability to search across multiple vector stores and apply attribute-based filtering to retrieve the most relevant content.
New enterprise-focused features include background mode, which allows for long-running asynchronous tasks, and reasoning summaries, designed to offer natural-language explanations of a model’s internal thought process, aiding debugging and transparency.