Bruk OpenAI Chat Completions API for samtaler. Dette er det klassiske OpenAI chat API-formatet.
/api/ai/v1/chat/completionsBearer YOUR_API_KEY| Parameter | Type | Påkrevd | Beskrivelse |
|---|---|---|---|
model | string | Påkrevd | Modellnavn, f.eks. deepseek-v4.1-flash, qwen3.8-max |
messages | array | Påkrevd | Meldinger i formatet |
max_tokens | integer | Valgfritt | Maksimalt antall output-tokens |
temperature | float | Valgfritt | Sampling-temperatur, styrer tilfeldighet (0-2) |
stream | boolean | Valgfritt | Aktiver streaming-svar, sett til true for SSE |
| Parameter | Type | Beskrivelse |
|---|---|---|
id | string | Unik svaridentifikator |
model | string | Faktisk brukt modell |
choices | array | Array med svarvalg, ta vanligvis den første |
usage | object | Statistikk over tokenbruk |
curl --location 'https://your-domain.com/api/ai/v1/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--data '{
"model": "deepseek-v4.1-flash",
"messages": [
{"role": "user", "content": "Hello, who are you?"}
],
"max_tokens": 1000,
"temperature": 0.7
}'import requests
response = requests.post(
"https://your-domain.com/api/ai/v1/chat/completions",
headers={
"Content-Type": "application/json",
"Authorization": "Bearer YOUR_API_KEY"
},
json={
"model": "deepseek-v4.1-flash",
"messages": [
{"role": "user", "content": "Hello, who are you?"}
],
"max_tokens": 1000,
"temperature": 0.7
}
)
print(response.json())curl --location 'https://your-domain.com/api/ai/v1/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--data '{
"model": "deepseek-v4.1-flash",
"messages": [{"role": "user", "content": "Hello"}],
"max_tokens": 1000,
"stream": true
}'