openai

Introducing GPT-4o-Mini-Search-Preview: Revolutionizing Web Search Integration

Tal Peretz

22 Mar 2025 — 1 min read

OpenAI has unveiled its latest innovation, the GPT-4o-Mini-Search-Preview, a tailored version of the GPT-4o mini model. This specialized model is designed specifically to enhance web search tasks and is readily accessible through the Chat Completions API.

What sets GPT-4o-Mini-Search-Preview apart? For starters, it features an impressive context window of 128,000 tokens, allowing for a more comprehensive understanding of input context. With a maximum output of 16,384 tokens per request, it ensures that your application receives detailed and accurate information.

Despite its robust capabilities, the GPT-4o-Mini-Search-Preview remains cost-effective. Input tokens are priced at just $0.15 per million, while output tokens cost $0.60 per million, making it an affordable choice for developers focused on integrating efficient web search functionalities.

This model is particularly beneficial for applications that need rapid and economical web search abilities, such as chatbots and applications that handle follow-up queries. It supports both text input and output, with image input available, broadening the scope of its applicability.

Available to all developers in preview, the GPT-4o-Mini-Search-Preview offers a seamless integration process with other tools within the Responses API. Its release marks a significant advancement in enabling more dynamic and interactive user experiences in web search applications.

Embrace the future of web search with GPT-4o-Mini-Search-Preview and elevate your application's capabilities today!

Introducing Google's Gemini 2.5 Pro Experimental: The Next Frontier in AI on Vertex AI

Google recently unveiled its most advanced AI model yet, Gemini 2.5 Pro Experimental (gemini-2.5-pro-exp-03-25), available soon on Vertex AI. Designed to excel in complex reasoning, coding, math, and science tasks, this model sets a new standard in AI capabilities. Enhanced Intelligence and Capabilities Gemini 2.5 Pro Experimental

Unlocking Multimodal AI Capabilities with Vertex AI's MultimodalEmbedding@001

As AI applications continue to evolve, businesses increasingly rely on multimodal data—combining text, images, videos, and audio—to enhance user experiences and extract deeper insights. Google's Vertex AI has recently introduced a powerful new embedding model, MultimodalEmbedding@001, designed specifically to handle diverse data types within one

Unlocking the Power of OpenAI's GPT-4o-Transcribe for Audio Transcription

In the ever-evolving landscape of artificial intelligence, OpenAI has once again pushed the boundaries with its latest offering: GPT-4o-Transcribe. Designed specifically for audio transcription, this advanced language model is poised to revolutionize the way we convert spoken language into written text. One of the standout features of GPT-4o-Transcribe is its

Introducing Gpt-4o-Mini-Transcribe: Streamlined Audio Transcription by OpenAI

The landscape of audio transcription has been revolutionized with the introduction of OpenAI's latest model, Gpt-4o-Mini-Transcribe. This new language model offers a powerful, efficient, and cost-effective solution for converting audio into text. With an input price of just $1.25 per million tokens and an output price of

Read more

Introducing Google's Gemini 2.5 Pro Experimental: The Next Frontier in AI on Vertex AI

Unlocking Multimodal AI Capabilities with Vertex AI's MultimodalEmbedding@001

Unlocking the Power of OpenAI's GPT-4o-Transcribe for Audio Transcription

Introducing Gpt-4o-Mini-Transcribe: Streamlined Audio Transcription by OpenAI