AIAI Gateway/Dokumentasi API/Chat Completions

API Chat Completions OpenAI

Gunakan API Chat Completions OpenAI untuk perbualan. Ini ialah format API chat OpenAI klasik.

Titik Akhir

POST/api/ai/v1/chat/completions

Pengesahan

AuthorizationDiperlukan

Bearer YOUR_API_KEY

Permintaan

Parameter	Jenis	Diperlukan	Keterangan
`model`	string	Diperlukan	Nama model, cth. deepseek-v4.1-flash, qwen3.8-max
`messages`	array	Diperlukan	Array mesej dalam format berikut
`max_tokens`	integer	Opsional	Jumlah maksimum token output
`temperature`	float	Opsional	Suhu pensampelan, mengawal keacakan (0-2)
`stream`	boolean	Opsional	Aktifkan respons streaming, tetapkan ke true untuk SSE

Respons

Parameter	Jenis	Keterangan
`id`	string	Pengecam respons unik
`model`	string	Model sebenar yang digunakan
`choices`	array	Array pilihan respons, biasanya ambil yang pertama
`usage`	object	Statistik penggunaan token

Contoh

cURL

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
  }'

Python

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())

Contoh Streaming

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
  }'

← Responses Anthropic Messages →

Permintaan

Parameter	Jenis	Diperlukan	Keterangan
`model`	string	Diperlukan	Nama model, cth. deepseek-v4.1-flash, qwen3.8-max
`messages`	array	Diperlukan	Array mesej dalam format berikut
`max_tokens`	integer	Opsional	Jumlah maksimum token output
`temperature`	float	Opsional	Suhu pensampelan, mengawal keacakan (0-2)
`stream`	boolean	Opsional	Aktifkan respons streaming, tetapkan ke true untuk SSE

Parameter

Jenis

Keterangan

id

string

Pengecam respons unik

model

string

Model sebenar yang digunakan

choices

array

Array pilihan respons, biasanya ambil yang pertama

usage

object

Statistik penggunaan token

Contoh

cURL

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
  }'

Python

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())

Contoh Streaming

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
  }'