NEAR AI Cloud: Web Search
Give models access to live web results through Chat Completions
NEAR AI Cloud provides a built-in server-side web search tool for Chat Completions. 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.
[!WARNING]
The stateless Responses API does not execute built-in
web_searchorweb_context_searchtools. Use Chat Completions as shown below, or expose search as a custom function and execute it in your application.
Chat Completions API
web_context_search is also available on /v1/chat/completions. It requires stream: true:
curl https://cloud-api.near.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "z-ai/glm-5.2",
"messages": [{"role": "user", "content": "What is the current population of Tokyo? One short sentence."}],
"tools": [{"type": "web_context_search"}],
"stream": true
}'
The stream interleaves the search activity with the answer:
delta.tool_callschunks show the model composing its search query (function nameweb_context_search)- a
delta.nearai_tool_resultchunk carries the search results that were injected back into the model's context - regular
delta.content(anddelta.reasoning_content) chunks stream the final answer
This makes it easy to display "searching the web…" states and surface sources in your UI.
[!NOTE]
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
- Stateless Responses — client-managed functions and unsupported built-in tools
- OpenAI Compatibility — SDK setup
- Prompt Caching — search context benefits from cache-read pricing on repeated turns