OpenAIOpenAI has updated its Responses API to support image results in addition to text when using the web search tool. This allows developers to build applications that can surface visual content like products, places, and visual references directly from the web. The update enhances the multimodal capabilities of AI applications by providing richer, visually-grounded responses.
search_content_types parameter to include image, optionally adding text for supporting context. Image-specific behaviors, such as the max_results and caption for descriptions, are controlled via image_settings.This capability matters as AI systems increasingly move towards multimodal understanding and generation, allowing applications to provide more comprehensive and visually-rich outputs. It aligns with a broader industry trend, as seen with Google's multimodal RAG for its Gemini File Search, to integrate diverse data types for enhanced grounding and verifiable results.
Applications can use the Responses API with the web_search tool and models like gpt-5.5 to retrieve current or web-grounded visuals. Developers can also refine search results by specifying user_location (country, city, region) or applying filters for allowed or blocked domains. For in-depth research, the return_token_budget can be set to unlimited to remove the default token cap on search results.
Your app can now search the web for images. Web search in the Responses API now supports image results in addition to text results, so you can build apps that surface products, places, visual references, and source links for inspiration. https://t.co/Oyl4cS4Jdu
Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →
More like this
OpenAIMar 15
OpenRouterApr 24
GoogleMay 5
Google AI StudioApr 30