Up to 7.2× the speed of standard llama.cpp Runs 100% on your PC
Free for personal use
Download free

Server info

GET/
Free: not countedBase URL http://localhost:1234/v1
Local API Guide contents

Overview

Returns a small description of the server. It is outside /v1, so it never needs the API key: use it to check that the Local API server is running before you send real requests.

Request

No parameters.

Response

FieldDescription
namestringAlways 5090Ai local API.
openai_compatiblebooleanAlways true.
endpointsstring[]The endpoints this version serves.

Example

curl http://localhost:1234/
Response
{
  "name": "5090Ai local API",
  "openai_compatible": true,
  "endpoints": ["/v1/models", "/v1/chat/completions", "/v1/completions", "/v1/embeddings", "/v1/web/search",
                "/v1/knowledge/collections", "/v1/knowledge/documents", "/v1/knowledge/search"]
}

Errors

None: if the server is off, the connection is refused.