POST
POST /vector_stores/{vector_store_id}/search — OpenAI API
OpenAI API key (required); https://api.openai.com/v1
OpenAI APISearch vector store
- Base URL
- https://api.openai.com/v1
- Auth
- Authorization: Bearer <OPENAI_API_KEY>
- Last verified
- 2026-10-20 · upstream hash matched
Actions Try in browser→
Agents: curl -H "Accept: text/markdown" this URL
→ 299 tokens · Vary: Accept
→ 299 tokens · Vary: Accept
Critical gotchas
The Responses API is the primary interface for new text and tool workflows; Chat Completions remains a separate compatibility API.
Audio transcription uploads use multipart form data rather than a JSON request body.
cURL
curl -X POST 'https://api.openai.com/v1/vector_stores/vs_abc123/search' \ -H "Authorization: Bearer $OPENAI_API_KEY" \ -H 'Content-Type: application/json' \ -d '{ "query": "example-query"}'
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| vector_store_id | path | string | Yes | The ID of the vector store to search. |
| query | body | string | Yes | A query string for a search |
| rewrite_query | body | boolean | No | Whether to rewrite the natural language query for vector search. |
| max_num_results | body | integer | No | The maximum number of results to return. This number should be between 1 and 50 inclusive. |
| filters | body | object | No | A filter to apply based on file attributes. |
| ranking_options | body | object | No | Ranking options for search. |
Response 200 OK
{
"object": "vector_store.search_results.page",
"search_query": [
"string"
],
"data": [
{
"file_id": "string",
"filename": "string",
"score": 0,
"attributes": {},
"content": [
{
"type": "text",
"text": "string"
}
]
}
],
"has_more": true,
"next_page": "string"
} Get a free OpenAI API key → sponsored Affiliate link - we may earn a commission, at no extra cost to you.