Google 会使用 AI 技术将内容翻译成您偏好的语言。AI 翻译可能包含错误。

OpenAI 兼容性

您可以使用 OpenAI 库（Python、TypeScript 和 JavaScript）以及 REST API 来访问 Gemini 模型。在 Gemini Enterprise Agent Platform 中使用 OpenAI 库时，仅支持 Google Cloud Auth。如果您尚未使用 OpenAI 库，请直接调用 Gemini API。如果您使用的是 OpenAI 库，并想迁移到 Agent Platform SDK，请参阅从 OpenAI SDK 迁移到 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)

请注意与标准 OpenAI 客户端配置的以下差异：

api_key=credentials.token：使用从Google Cloud 应用默认凭证获得的 OAuth 访问令牌。
base_url：指示 OpenAI 库将请求发送到与 Agent Platform OpenAI 兼容的端点，而不是默认网址。
model="google/gemini-3.5-flash"：选择 Agent Platform 上托管的兼容 Gemini 模型。

正在思考

Gemini 3 模型会在返回回答之前生成内部推理过程，从而提高在复杂的多步骤任务中的性能。在 Gemini API 中，thinking_level 参数用于控制离散层级（MINIMAL、LOW、MEDIUM 和 HIGH）的推理深度。

在与 OpenAI 兼容的 Chat Completions API 中，您可以使用 reasoning_effort 参数（"minimal"、"low"、"medium" 或 "high"）控制推理深度，该参数会映射到 Gemini 3 模型的相应 thinking_level 设置。

省略 reasoning_effort 会使用模型的默认思考配置。

如需通过 OpenAI 兼容的 API 直接控制思考配置参数，请使用 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-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)

流式

Gemini API 支持流式回答。

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)

函数调用

函数调用功能可让您更轻松地从生成式模型获取结构化数据输出，并且在 Gemini API 中受支持。

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)

图片理解

Gemini 模型是原生多模态模型，支持许多常见的视觉任务。

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])

生成图片

REST

在使用任何请求数据之前，请先进行以下替换：

PROJECT_ID：您的项目 ID。。

如需发送您的请求，请展开以下选项之一：

curl（Linux、macOS 或 Cloud Shell）

注意：以下命令假定您已使用您的用户账号通过运行 gcloud init 或 gcloud auth login 登录 gcloud CLI，或者使用了 Cloud Shell，这会使您自动登录 gcloud CLI。您可以通过运行 gcloud auth list 来检查当前的活跃账号。

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

cat > request.json << 'EOF'
{
  "model": "google/gemini-3.1-flash-image",
  "messages": [{
    "role": "user",
    "content": "Generate an image of a banana."
  }],
  "modalities": ["image", "text"]
}
EOF

然后，执行以下命令以发送 REST 请求：

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：以下命令假定您已使用您的用户账号通过运行 gcloud init 或 gcloud auth login 登录 gcloud CLI。您可以通过运行 gcloud auth list 来检查当前的活跃账号。

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

@'
{
  "model": "google/gemini-3.1-flash-image",
  "messages": [{
    "role": "user",
    "content": "Generate an image of a banana."
  }],
  "modalities": ["image", "text"]
}
'@  | Out-File -FilePath request.json -Encoding utf8

然后，执行以下命令以发送 REST 请求：

$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

您应该收到类似以下内容的 JSON 响应：

{
  "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-3.1-flash-image",
  "object":"chat.completion",
  "system_fingerprint":"",
  "usage": {
    "completion_tokens":1299,
    "prompt_tokens":7,
    "total_tokens":1306
  }
}

音频理解

以下示例展示了如何分析音频输入：

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)

结构化输出

Gemini 模型可以输出采用您定义的任何结构的 JSON 对象。

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)

当前限制

使用与 OpenAI 兼容的 API 时，请考虑以下限制：

默认情况下，访问令牌的有效期为 1 小时。过期后，必须刷新。如需了解详情，请参阅刷新凭据。

后续步骤

使用 Google 生成式 AI 库直接调用 Gemini 模型。
查看更多使用 OpenAI 兼容语法调用 Chat Completions API 的示例。
如需查看受支持的 Gemini 模型和参数，请参阅将 OpenAI 库与 Agent Platform 搭配使用。

OpenAI 兼容性 使用集合让一切井井有条 根据您的偏好保存内容并对其进行分类。

Python

正在思考

Python

流式

Python

函数调用

Python

图片理解

Python

生成图片

REST

curl（Linux、macOS 或 Cloud Shell）

PowerShell (Windows)

音频理解

Python

结构化输出

Python

当前限制

后续步骤

OpenAI 兼容性