Warm the GPU services
curl --request GET \
--url https://api.lightdrift.ai/v1/warm \
--header 'X-API-Key: <api-key>'import requests
url = "https://api.lightdrift.ai/v1/warm"
headers = {"X-API-Key": "<api-key>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {'X-API-Key': '<api-key>'}};
fetch('https://api.lightdrift.ai/v1/warm', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"embed": {
"state": "warm",
"took_s": 161.2,
"checked": "2026-09-13T19:05:25Z"
},
"rerank": {
"state": "warming",
"for_s": 42
},
"ready": false,
"hint": "poll every 10 s until ready; a cold start takes 2.5-4 min"
}Starts warming the embedding and reranking services in the background and reports their last-known state. A cold start takes about 2.5 to 4 minutes; call this at the start of an agent session and poll every 10 s until ready is true, instead of paying the cold start inside the first search. Idle services shut down after 1 hour without requests.
GET
/
v1
/
warm
Warm the GPU services
curl --request GET \
--url https://api.lightdrift.ai/v1/warm \
--header 'X-API-Key: <api-key>'import requests
url = "https://api.lightdrift.ai/v1/warm"
headers = {"X-API-Key": "<api-key>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {'X-API-Key': '<api-key>'}};
fetch('https://api.lightdrift.ai/v1/warm', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"embed": {
"state": "warm",
"took_s": 161.2,
"checked": "2026-09-13T19:05:25Z"
},
"rerank": {
"state": "warming",
"for_s": 42
},
"ready": false,
"hint": "poll every 10 s until ready; a cold start takes 2.5-4 min"
}Authorizations
Your Lightdrift API key. Usage is metered per query.
Response
Current warm state.