OpenAI introduces Web Search tool within its models to search the web for latest information before generating a response

OpenAI is offering a new Web Search tool that allows the OpenAI models to access up-to-date information from the internet and provide answers with sourced citations. To enable this, use the web search tool in the Responses API, or in some cases, Chat Completions.

Three main types of web search available with OpenAI models

• Non‑reasoning web search: The non-reasoning model sends the user’s query to the web search tool, which returns the response based on top results. There’s no internal planning, and the model simply passes along the search tool’s responses. This method is fast and ideal for quick lookups.
• Agentic search with reasoning models is an approach where the model actively manages the search process. It can perform web searches as part of its chain of thought, analyze results, and decide whether to keep searching. This flexibility makes agentic search well-suited to complex workflows, but it also means searches take longer than quick lookups. For example, you can adjust GPT-5’s reasoning level to change both the depth and latency of the search.
• Deep research is a specialized, agent-driven method for in-depth, extended investigations by reasoning models. The model conducts web searches as part of its chain of thought, often tapping into hundreds of sources. Deep research can run for several minutes and is best used with background mode. These tasks typically use models like o3-deep-research, o4-mini-deep-research, or gpt-5 with reasoning level set to high.

Model responses that use the web search tool include two parts: web_search_call output item and a message output item. By default, the model’s response will include inline citations for URLs found in the web search results.

Some other features in Web Search include- Domain filtering that lets users limit results to a specific set of domains, and Sources that returns the complete list of URLs the model consulted when forming its response. Also, to refine search results based on geography, you can specify an approximate user location using country, city, region, and/or timezone.

Limitations

• Web search is currently not supported in GPT-5 with minimal reasoning, and gpt-4.1-nano
• When used as a tool in the Responses API, web search has the same tiered rate limits as the models above.
• Web search is limited to a context window size of 128000 (even with gpt-4.1 and gpt-4.1-mini models).

API compatibility

Web search is available in the Responses API as the generally available version of the tool, web_search, as well as the earlier tool version, web_search_preview. To use web search in the Chat Completions API, use the specialized web search models gpt-5-search-api, gpt-4o-search-preview, and gpt-4o-mini-search-preview.