Introducing the YOU API: Web-scale search for LLMs


Large language models (LLMs) have opened up new possibilities for transforming various sectors of the economy. These models have the capacity to absorb vast amounts of text, enabling them to generate outputs that can automate many tasks that depend on language. However, there are three main problems with LLMs that we aim to address:

  • They often hallucinate — producing outputs that lack grounding in real-world information.
  • They may generate content without supporting it with credible sources, which makes it difficult to verify accuracy.
  • They struggle to keep up with the ever-changing events happening worldwide, leading to outdated responses.


To tackle these challenges, we are launching the YOU API. It offers a comprehensive suite of tools designed to help developers ground the output of LLMs in the most recent, accurate, and relevant information available. By leveraging the power of this API, developers can ensure that their LLM-generated content is supported by reliable sources and up-to-date data.

The API is launching with three dedicated endpoints:

  1. Web Search — Provides search results similar to Google or Bing, except that instead of short snippets designed to entice humans to click the links, we provide many long snippets designed to provide an LLM the most relevant information needed to generate the best response. This is akin to but more powerful and faster than SERP APIs.
  2. News — Similar to Web Search, but exclusively news results for applications that primarily rely on current events.
  3. RAG — Our end-to-end solution that pairs our Web Search results with an LLM to generate a response with fewer hallucinations and more facts.

You can learn more about how to use each of these at The Web Search, News, and RAG endpoints are available at You can access a free trial for the Web Search and News endpoints.

Evaluating the YOU API

We evaluate the effectiveness of the YOU API by adapting several academic question answering datasets to the “open web” setting: passages typically provided to an AI as context must instead be retrieved from the web itself. This evaluation method demands much more of the system as a whole than the academic benchmarks from which they are derived. This provides a more realistic and practical assessment of the performance of web scale RAG systems.

In this first set of results below, we compare using, Google, or Bing search results together with the default LLM deployed in our RAG endpoint. The YOU API comes out ahead on every benchmark.

Higher F1 scores across the board show that the LLM is more likely to generate a correct response given search results from the YOU API than even Google search results. The LLM used in these experiments has a context window of 16k tokens and is most similar to OpenAI’s ChatGPT 3.5 Turbo model. Recall numbers have an even wider margin than the F1 scores, which suggests that the LLM cannot fully make use of the extra information that the Web Search API provides to generate better answers.

Recall here means that the correct answer (based on the original ground truth phrase from the datasets) is included in the snippets that are returned by the API:

FreshQA RecallSquadV2 RecallHotpotQA RecallMS MARCO Recall

Using an LLM with a 16k context window filled with snippets to answer questions:

FreshQA SquadV2 F1HotpotQA F1MS MARCO

If you would like to evaluate your full scale web-index for LLMs on these datasets, please email us at [email protected] and we can share the evaluation benchmarks.

Future work

We will continue to work on enhancing the API’s functionality and user experience. Efforts are being made to make the APIs more intuitively conversational, allowing users to handle context effortlessly. Moreover, intermediate modules like query rewriting will be exposed as new endpoints, enabling developers to customize their usage of the YOU API according to their specific needs. Additionally, the API team aims to incorporate agent-like capabilities, similar to those of’s Agent and Deep Research modes, making all the functionality of accessible through the API.


The YOU API empowers developers to overcome the limitations of LLMs by providing them with the tools to ground their outputs in the most recent, accurate, and relevant information. With its superior performance compared to existing search providers and its ability to adapt to various LLMs, the API is revolutionizing the way developers can leverage the power of LLMs in their applications. We hope this frees up knowledge on the web from the very limited and restrictive options currently available. We are excited to see the many applications being built and will support our ecosystem with future innovation with up-to-date knowledge from the web.

Learn more about how to use the API at Visit to access the Web Search, News, and RAG endpoints. If you have any questions, please email [email protected].

Yay, you’ve read the whole article. If you enjoyed this story, please recommend 👏 and share to help others find it!