Se puede acceder a los modelos de Gemini con las bibliotecas de OpenAI (Python, TypeScript y JavaScript) junto con la API de REST. Solo se admite la autenticación de Google Cloud con la biblioteca de OpenAI en Gemini Enterprise Agent Platform. Si todavía no usas las bibliotecas de OpenAI, llama a la API de Gemini directamente. Si usas bibliotecas de OpenAI y quieres migrar a los SDKs de Agent Platform, consulta Migra del SDK de OpenAI al SDK de IA generativa de Google.
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)
Ten en cuenta las siguientes diferencias con respecto a la configuración estándar del cliente de OpenAI:
api_key=credentials.token: Usa un token de acceso de OAuth obtenido de las credenciales predeterminadas de la aplicación deGoogle Cloud .base_url: Indica a la biblioteca de OpenAI que envíe solicitudes al extremo compatible con OpenAI de Agent Platform en lugar de la URL predeterminada.model="google/gemini-3.5-flash": Selecciona un modelo de Gemini compatible alojado en Agent Platform.
Razonamiento
Los modelos de Gemini 3 generan un proceso de razonamiento interno antes de
devolver una respuesta, lo que mejora el rendimiento en tareas complejas de varios pasos. En la
API de Gemini, el
parámetro thinking_level
controla la profundidad del razonamiento en niveles discretos (MINIMAL, LOW, MEDIUM y
HIGH).
En la API de Chat Completions compatible con OpenAI, controlas la profundidad del razonamiento con
el parámetro reasoning_effort ("minimal", "low", "medium" o
"high"), que se asigna al parámetro de configuración thinking_level correspondiente para
los modelos de Gemini 3.
Si se omite reasoning_effort, se usa la configuración de pensamiento predeterminada del modelo.
Para controlar directamente los parámetros de configuración de razonamiento desde la API compatible con OpenAI, usa
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)
Transmisión
La API de Gemini admite respuestas de transmisión.
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)
Llamada a función
La llamada a funciones facilita la obtención de resultados de datos estructurados a partir de modelos generativos y es compatible con la API de Gemini.
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)
Comprensión de imágenes
Los modelos de Gemini son multimodales de forma nativa y admiten muchas tareas de visión comunes.
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])
Comprensión de audio
En el siguiente ejemplo, se muestra cómo analizar la entrada de 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)
Resultados estructurados
Los modelos de Gemini pueden generar objetos JSON en cualquier estructura que definas.
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)
Limitaciones actuales
Ten en cuenta la siguiente limitación cuando uses la API compatible con OpenAI:
- De forma predeterminada, los tokens de acceso están activos durante 1 hora. Después de que vencen, se deben actualizar. Para obtener más información, consulta Actualiza tus credenciales.
¿Qué sigue?
Usa las bibliotecas de IA generativa de Google para llamar a los modelos de Gemini directamente.
Consulta más ejemplos de uso de la API de Chat Completions con la sintaxis compatible con OpenAI.
Consulta los modelos y parámetros de Gemini compatibles en Usa bibliotecas de OpenAI con Agent Platform.