Introducing support for remote MCP servers, image generation, Code Interpreter, and more in the Responses API.

Image generation is now available as a tool with the Responses API. Stream previews of images as they’re being generated, and enable multi-turn edits to granularly refine images step-by-step.

Code Interpreter now works in the Responses API for data analysis, math, coding, and deep image understanding (“thinking with images”). OpenAI o3 and o4-mini have improved on benchmarks like Humanity’s Last Exam using this tool in their chain-of-thought!

File search is now supported with reasoning models to pull relevant chunks from documents, search across up to two vector stores, and apply attribute filtering with arrays.

We’re also adding new features to the Responses API: 🔙 Background mode to kick off async tasks: 🧠 Reasoning summaries to concisely see the model’s internal chain-of-thought 🔐 Encrypted reasoning items to reuse reasoning items across API requests for ZDR orgs:

Here’s @nikunjhanda and @stevenheidel to show you how MCP, reasoning, and multiple Responses API tools can work together. Read more in our blog:

API testing of interfaces is critical to determine if they meet requirements for functionality, reliability, performance, and security. Check out RTTS - the automated testing experts since 1996. #API #testautomation #integrationtest

This is huge But where is my o3-pro?

@zapier is very excited to be a part of this launch -- connect 8k apps with one endpoint! 👌

Every time OpenAI ships an MCP feature, @basedjensen dies a little inside

This is the kind of update that doesn’t make headlines… until someone builds something massive with it.

$AINARA has a forward-looking vision! Always staying ahead and leading the way! @AinaraApp #MCP #AICoins #AIAgent #Solana #CryptoTrends