OpenAI 相容性

您可以使用 OpenAI 程式庫 (Python 和 TypeScript/JavaScript) 和 REST API 存取 Gemini 模型。Vertex AI 中的 OpenAI 程式庫僅支援 Google Cloud Auth。如果您尚未開始使用 OpenAI 程式庫，建議您直接呼叫 Gemini API。如果您使用 OpenAI 程式庫，並想遷移至 Vertex AI SDK，請參閱「從 OpenAI SDK 遷移至 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-2.0-flash-001",
  messages=[
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain to me how AI works"}
  ]
)

print(response.choices[0].message)

有何不同之處呢？

api_key=credentials.token：如要使用 Google Cloud 驗證，請使用範例程式碼取得Google Cloud 驗證權杖。
base_url：這會告知 OpenAI 程式庫將要求傳送至 Google Cloud，而非預設網址。
model="google/gemini-2.0-flash-001"：從 Vertex 代管的模型中，選擇相容的 Gemini 模型。

思考

Gemini 2.5 模型經過訓練，能夠思考複雜問題，因此推論能力大幅提升。Gemini API 隨附「思考預算」參數，可精細控管模型的思考量。

與 Gemini API 不同，OpenAI API 提供三種思考控制等級：「低」、「中」和「高」，這些等級會在幕後對應至 1K、8K 和 24K 的思考權杖預算。

完全不指定推理工作量，就等於不指定思考預算。

如要透過與 OpenAI 相容的 API 更直接地控管思考預算和其他思考相關設定，請使用 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-2.5-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)

串流

Gemini API 支援串流回應。

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-2.0-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)

函式呼叫

有了函式呼叫功能，就能更輕鬆地從生成式模型取得結構化資料輸出內容，且 Gemini API 支援這項功能。

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-2.0-flash",
  messages=messages,
  tools=tools,
  tool_choice="auto"
)

print(response)

圖像解讀

Gemini 模型原生支援多種形式的內容，且在許多常見的視覺化工作中，都能提供同級最佳的效能。

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-2.0-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])

生成圖片

REST

設定環境後，您可以使用 REST 測試文字提示。下列範例會將要求傳送至發布商模型端點。

使用任何要求資料之前，請先修改下列項目的值：

PROJECT_ID：您的專案 ID。

請展開以下其中一個選項，以傳送要求：

curl (Linux、macOS 或 Cloud Shell)

注意：下列指令假設您已執行 gcloud init 或 gcloud auth login，透過使用者帳戶登入 gcloud CLI，或已使用 Cloud Shell 自動登入 gcloud CLI。您可以執行 gcloud auth list，查看目前使用的帳戶。

將要求主體儲存在名為 request.json 的檔案中。在終端機中執行下列指令，在目前目錄中建立或覆寫這個檔案：

cat > request.json << 'EOF'
{
  "model": "google/gemini-2.5-flash-image-preview",
  "messages": [{
    "role": "user",
    "content": "Generate an image of a banana."
  }],
  "modalities": ["image", "text"]
}
EOF

然後執行下列指令，傳送 REST 要求：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/chat/completions"

PowerShell (Windows)

注意：下列指令假設您已執行 gcloud init 或 gcloud auth login，透過使用者帳戶登入 gcloud CLI。您可以執行 gcloud auth list，查看目前使用的帳戶。

將要求主體儲存在名為 request.json 的檔案中。在終端機中執行下列指令，在目前目錄中建立或覆寫這個檔案：

@'
{
  "model": "google/gemini-2.5-flash-image-preview",
  "messages": [{
    "role": "user",
    "content": "Generate an image of a banana."
  }],
  "modalities": ["image", "text"]
}
'@  | Out-File -FilePath request.json -Encoding utf8

然後執行下列指令，傳送 REST 要求：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/chat/completions" | Select-Object -Expand Content

您應該會收到如下的 JSON 回覆：

{
  "choices": [{
    "finish_reason": "stop",
    "index": 0,
    "image": {
      "data":"IMAGE_DATA",
      "extra_content": {
        "google": {
          "mime_type":"image/png"
        }
      }
    },
    "content":"Here is an image of a banana: ",
    "role":"assistant"
  }],
  "created":1757099999,
  "id":"sample_response_id",
  "model":"google/gemini-2.5-flash-image-preview",
  "object":"chat.completion",
  "system_fingerprint":"",
  "usage": {
    "completion_tokens":1299,
    "prompt_tokens":7,
    "total_tokens":1306
  }
}

音訊理解

分析音訊輸入內容：

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="gemini-2.0-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)

結構化輸出內容

Gemini 模型可以輸出您定義的任何結構的 JSON 物件。

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-2.0-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)

目前限制

存取權杖的預設效期為 1 小時。過期後必須重新整理。詳情請參閱這個程式碼範例。

後續步驟

使用 Google Gen AI 程式庫，發揮 Gemini 的潛力。
如要查看更多使用 Chat Completions API 的範例，請參閱 OpenAI 相容語法。
請參閱總覽頁面，瞭解支援哪些 Gemini 模型和參數。

OpenAI 相容性 透過集合功能整理內容 你可以依據偏好儲存及分類內容。

Python

思考

Python

串流

Python

函式呼叫

Python

圖像解讀

Python

生成圖片

REST

curl (Linux、macOS 或 Cloud Shell)

PowerShell (Windows)

音訊理解

Python

結構化輸出內容

Python

目前限制

後續步驟

OpenAI 相容性