Skip to main content
NEAR AI Cloud provides built-in server-side web search tools for the Responses and Chat Completions APIs. The model decides when to search, the platform executes the search, and the results are fed back to the model without tool-handling code on your side. Web search is billed per request as a platform service in addition to model tokens. Current pricing is available from the public /v1/services endpoint.

Responses API

Add web_search to the tools array. Set count to control the maximum number of results returned by each search in this request:
count is optional and accepts integers from 0 through 20. When set, it overrides the result count chosen by the model for every web_search call in the request. Omit it to let the model choose. With count: 0, search calls return empty results without calling the search provider; the model can still make a search tool call. Fewer results than requested may be returned. count applies to web_search in the Responses API. You can also use web_context_search in Responses, but it does not accept this request-level count setting. The response includes search activity as web_search_call output items alongside the model’s answer.

Chat Completions API

web_context_search is also available on /v1/chat/completions. It requires stream: true:
The stream interleaves the search activity with the answer:
  1. delta.tool_calls chunks show the model composing its search query (function name web_context_search)
  2. a delta.nearai_tool_result chunk carries the search results that were injected back into the model’s context
  3. regular delta.content (and delta.reasoning_content) chunks stream the final answer
This makes it easy to display “searching the web…” states and surface sources in your UI.
Unlike client-side function calling, you never receive a finish_reason: "tool_calls" response that you have to answer — the search loop runs entirely server-side, on infrastructure operated by NEAR AI.

See Also