Model Gemini dapat diakses menggunakan library OpenAI (Python, TypeScript, dan JavaScript) bersama dengan REST API. Hanya Google Cloud Auth yang didukung menggunakan library OpenAI di Gemini Enterprise Agent Platform. Jika Anda belum menggunakan library OpenAI, panggil Gemini API secara langsung. Jika Anda menggunakan library OpenAI dan ingin bermigrasi ke SDK Agent Platform, lihat Bermigrasi dari OpenAI SDK ke Google Gen AI SDK.
Python
import openai
from google.auth import default
import google.auth.transport.requests
# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "global"
# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
credentials.refresh(google.auth.transport.requests.Request())
# OpenAI Client
client = openai.OpenAI(
base_url=f"https://aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/openapi",
api_key=credentials.token
)
response = client.chat.completions.create(
model="google/gemini-3.5-flash",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Explain to me how AI works"}
]
)
print(response.choices[0].message)
Perhatikan perbedaan berikut dari konfigurasi klien OpenAI standar:
api_key=credentials.token: Menggunakan token akses OAuth yang diperoleh dari Google Cloud Kredensial Default Aplikasi.base_url: Mengarahkan library OpenAI untuk mengirim permintaan ke endpoint yang kompatibel dengan OpenAI di Agent Platform, bukan ke URL default.model="google/gemini-3.5-flash": Memilih model Gemini yang kompatibel yang dihosting di Agent Platform.
Penalaran
Model Gemini 3 menghasilkan proses penalaran internal sebelum
menampilkan respons, sehingga meningkatkan performa pada tugas multi-langkah yang kompleks. Di
Gemini API,
parameter thinking_level
mengontrol kedalaman penalaran di berbagai tingkat diskret (MINIMAL, LOW, MEDIUM, dan
HIGH).
Di Chat Completions API yang kompatibel dengan OpenAI, Anda mengontrol kedalaman penalaran dengan
parameter reasoning_effort ("minimal", "low", "medium", atau
"high"), yang dipetakan ke setelan thinking_level yang sesuai untuk
model Gemini 3.
Jika reasoning_effort dihilangkan, konfigurasi penalaran default model akan digunakan.
Untuk kontrol langsung atas parameter konfigurasi penalaran dari
API yang kompatibel dengan OpenAI, gunakan
extra_body.google.thinking_config.
Python
import openai
from google.auth import default
import google.auth.transport.requests
# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "global"
# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
credentials.refresh(google.auth.transport.requests.Request())
# OpenAI Client
client = openai.OpenAI(
base_url=f"https://aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/openapi",
api_key=credentials.token
)
response = client.chat.completions.create(
model="google/gemini-3.5-flash",
reasoning_effort="low",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{
"role": "user",
"content": "Explain to me how AI works"
}
]
)
print(response.choices[0].message)
Streaming
Gemini API mendukung respons streaming.
Python
import openai
from google.auth import default
import google.auth.transport.requests
# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "global"
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
credentials.refresh(google.auth.transport.requests.Request())
client = openai.OpenAI(
base_url=f"https://aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/openapi",
api_key=credentials.token
)
response = client.chat.completions.create(
model="google/gemini-3.5-flash",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"}
],
stream=True
)
for chunk in response:
print(chunk.choices[0].delta)
Panggilan fungsi
Pemanggilan fungsi memudahkan untuk mendapatkan output data terstruktur dari model generatif dan didukung di Gemini API.
Python
import openai
from google.auth import default
import google.auth.transport.requests
# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "global"
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
credentials.refresh(google.auth.transport.requests.Request())
client = openai.OpenAI(
base_url=f"https://aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/openapi",
api_key=credentials.token
)
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. Chicago, IL",
},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
},
"required": ["location"],
},
}
}
]
messages = [{"role": "user", "content": "What's the weather like in Chicago today?"}]
response = client.chat.completions.create(
model="google/gemini-3.5-flash",
messages=messages,
tools=tools,
tool_choice="auto"
)
print(response)
Pemahaman gambar
Model Gemini secara native bersifat multimodal dan mendukung banyak tugas vision umum.
Python
from google.auth import default
import google.auth.transport.requests
import base64
from openai import OpenAI
# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "global"
# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
credentials.refresh(google.auth.transport.requests.Request())
# OpenAI Client
client = openai.OpenAI(
base_url=f"https://aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/openapi",
api_key=credentials.token,
)
# Function to encode the image
def encode_image(image_path):
with open(image_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode('utf-8')
# Getting the base64 string
# base64_image = encode_image("Path/to/image.jpeg")
response = client.chat.completions.create(
model="google/gemini-3.5-flash",
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "What is in this image?",
},
{
"type": "image_url",
"image_url": {
"url": f"data:image/jpeg;base64,{base64_image}"
},
},
],
}
],
)
print(response.choices[0])
Pemahaman audio
Contoh berikut menunjukkan cara menganalisis input audio:
Python
from google.auth import default
import google.auth.transport.requests
import base64
from openai import OpenAI
# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "global"
# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
credentials.refresh(google.auth.transport.requests.Request())
# OpenAI Client
client = openai.OpenAI(
base_url=f"https://aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/openapi",
api_key=credentials.token,
)
with open("/path/to/your/audio/file.wav", "rb") as audio_file:
base64_audio = base64.b64encode(audio_file.read()).decode('utf-8')
response = client.chat.completions.create(
model="google/gemini-3.5-flash",
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "Transcribe this audio",
},
{
"type": "input_audio",
"input_audio": {
"data": base64_audio,
"format": "wav"
}
}
],
}
],
)
print(response.choices[0].message.content)
Output terstruktur
Model Gemini dapat menghasilkan objek JSON dalam struktur apa pun yang Anda tentukan.
Python
from google.auth import default
import google.auth.transport.requests
from pydantic import BaseModel
from openai import OpenAI
# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "global"
# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
credentials.refresh(google.auth.transport.requests.Request())
# OpenAI Client
client = openai.OpenAI(
base_url=f"https://aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/openapi",
api_key=credentials.token,
)
class CalendarEvent(BaseModel):
name: str
date: str
participants: list[str]
completion = client.beta.chat.completions.parse(
model="google/gemini-3.5-flash",
messages=[
{"role": "system", "content": "Extract the event information."},
{"role": "user", "content": "John and Susan are going to an AI conference on Friday."},
],
response_format=CalendarEvent,
)
print(completion.choices[0].message.parsed)
Batasan saat ini
Pertimbangkan batasan berikut saat menggunakan API yang kompatibel dengan OpenAI:
- Token akses berlaku selama 1 jam secara default. Setelah masa berlakunya habis, token harus diperbarui. Untuk mengetahui informasi selengkapnya, lihat Memperbarui kredensial.
Langkah berikutnya
Gunakan Library Google AI generatif untuk memanggil model Gemini secara langsung.
Lihat contoh lainnya menggunakan Chat Completions API dengan sintaksis yang kompatibel dengan OpenAI.
Lihat model dan parameter Gemini yang didukung di Menggunakan library OpenAI dengan Agent Platform.