AIAI Gateway/Dokumentasi API/Chat Completions

OpenAI API Pelengkapan Chat

Gunakan OpenAI API Pelengkapan Chat untuk percakapan. Ini adalah format API chat klasik OpenAI.

Endpoint

POST/api/ai/v1/chat/completions

Autentikasi

AuthorizationWajib

Bearer YOUR_API_KEY

Permintaan

Parameter	Tipe	Wajib	Deskripsi
`model`	string	Wajib	Nama model, mis. deepseek-v4.1-flash, qwen3.8-max
`messages`	array	Wajib	Array pesan dengan format berikut
`max_tokens`	integer	Opsional	Jumlah maksimum token output
`temperature`	float	Opsional	Suhu sampling, mengontrol keacakan (0-2)
`stream`	boolean	Opsional	Aktifkan respons streaming, setel ke true untuk SSE

Respons

Parameter	Tipe	Deskripsi
`id`	string	Pengenal respons unik
`model`	string	Model yang sebenarnya digunakan
`choices`	array	Array pilihan respons, biasanya gunakan 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	Tipe	Wajib	Deskripsi
`model`	string	Wajib	Nama model, mis. deepseek-v4.1-flash, qwen3.8-max
`messages`	array	Wajib	Array pesan dengan format berikut
`max_tokens`	integer	Opsional	Jumlah maksimum token output
`temperature`	float	Opsional	Suhu sampling, mengontrol keacakan (0-2)
`stream`	boolean	Opsional	Aktifkan respons streaming, setel ke true untuk SSE

Parameter

Tipe

Deskripsi

id

string

Pengenal respons unik

model

string

Model yang sebenarnya digunakan

choices

array

Array pilihan respons, biasanya gunakan 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
  }'