Ejemplos

Llama a Gemini con la API de Chat Completions

En el siguiente ejemplo, se muestra cómo enviar solicitudes sin transmisión:

REST

  curl -X POST \
    -H "Authorization: Bearer $(gcloud auth print-access-token)" \
    -H "Content-Type: application/json" \
  https://${LOCATION}-aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/${LOCATION}/endpoints/openapi/chat/completions \
  -d '{
    "model": "google/${MODEL_ID}",
    "messages": [{
      "role": "user",
      "content": "Write a story about a magic backpack."
    }]
  }'

Python

Antes de probar este ejemplo, sigue las instrucciones de configuración para Python que encontrarás en la guía de inicio rápido de Agent Platform sobre el uso de bibliotecas cliente.

Para autenticarte en Agent Platform, configura las credenciales predeterminadas de la aplicación. Para obtener más información, consulta Configura la autenticación para un entorno de desarrollo local.

from google.auth import default
import google.auth.transport.requests

import openai

# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "us-central1"

# 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://{location}-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": "user", "content": "Why is the sky blue?"}],
)

print(response)

En el siguiente ejemplo, se muestra cómo enviar solicitudes de transmisión a un modelo de Gemini con la API de Chat Completions:

REST

  curl -X POST \
    -H "Authorization: Bearer $(gcloud auth print-access-token)" \
    -H "Content-Type: application/json" \
  https://${LOCATION}-aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/${LOCATION}/endpoints/openapi/chat/completions \
  -d '{
    "model": "google/${MODEL_ID}",
    "stream": true,
    "messages": [{
      "role": "user",
      "content": "Write a story about a magic backpack."
    }]
  }'

Python

Antes de probar este ejemplo, sigue las instrucciones de configuración para Python que encontrarás en la guía de inicio rápido de Agent Platform sobre el uso de bibliotecas cliente.

from google.auth import default
import google.auth.transport.requests

import openai

# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "us-central1"

# 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://{location}-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": "user", "content": "Why is the sky blue?"}],
    stream=True,
)
for chunk in response:
    print(chunk)

Envía una instrucción y una imagen a la API de Gemini en Agent Platform de Gemini Enterprise

Python

Antes de probar este ejemplo, sigue las instrucciones de configuración para Python que encontrarás en la guía de inicio rápido de Agent Platform sobre el uso de bibliotecas cliente.


from google.auth import default
import google.auth.transport.requests

import openai

# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "us-central1"

# 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://{location}-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": "user",
            "content": [
                {"type": "text", "text": "Describe the following image:"},
                {
                    "type": "image_url",
                    "image_url": "gs://cloud-samples-data/generative-ai/image/scones.jpg",
                },
            ],
        }
    ],
)

print(response)

Llama a un modelo que se implementó por sí solo con la API de Chat Completions

En el siguiente ejemplo, se muestra cómo enviar solicitudes sin transmisión:

REST

  curl -X POST \
    -H "Authorization: Bearer $(gcloud auth print-access-token)" \
    -H "Content-Type: application/json" \
  https://aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/global/endpoints/${ENDPOINT}/chat/completions \
  -d '{
    "messages": [{
      "role": "user",
      "content": "Write a story about a magic backpack."
    }]
  }'

Python

Antes de probar este ejemplo, sigue las instrucciones de configuración para Python que encontrarás en la guía de inicio rápido de Agent Platform sobre el uso de bibliotecas cliente.

from google.auth import default
import google.auth.transport.requests

import openai

# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "us-central1"
# model_id = "gemma-2-9b-it"
# endpoint_id = "YOUR_ENDPOINT_ID"

# 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://{location}-aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/{endpoint_id}",
    api_key=credentials.token,
)

response = client.chat.completions.create(
    model=model_id,
    messages=[{"role": "user", "content": "Why is the sky blue?"}],
)
print(response)

En el siguiente ejemplo, se muestra cómo enviar solicitudes de transmisión a un modelo implementado por tu cuenta con la API de Chat Completions:

REST

    curl -X POST \
      -H "Authorization: Bearer $(gcloud auth print-access-token)" \
      -H "Content-Type: application/json" \
    https://aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/global/endpoints/${ENDPOINT}/chat/completions \
    -d '{
      "stream": true,
      "messages": [{
        "role": "user",
        "content": "Write a story about a magic backpack."
      }]
    }'

Python

Antes de probar este ejemplo, sigue las instrucciones de configuración para Python que encontrarás en la guía de inicio rápido de Agent Platform sobre el uso de bibliotecas cliente.

from google.auth import default
import google.auth.transport.requests

import openai

# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "us-central1"
# model_id = "gemma-2-9b-it"
# endpoint_id = "YOUR_ENDPOINT_ID"

# 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://{location}-aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/{endpoint_id}",
    api_key=credentials.token,
)

response = client.chat.completions.create(
    model=model_id,
    messages=[{"role": "user", "content": "Why is the sky blue?"}],
    stream=True,
)
for chunk in response:
    print(chunk)

`extra_body` ejemplos

Puedes usar el SDK o la API de REST para pasar extra_body.

Agregar `thought_tag_marker`

{
  ...,
  "extra_body": {
     "google": {
       ...,
       "thought_tag_marker": "..."
     }
   }
}

Agrega `extra_body` con el SDK

client.chat.completions.create(
  ...,
  extra_body = {
    'extra_body': { 'google': { ... } }
  },
)

`extra_content` ejemplos

Puedes completar este campo directamente con la API de REST.

`extra_content` con la cadena `content`

{
  "messages": [
    { "role": "...", "content": "...", "extra_content": { "google": { ... } } }
  ]
}

`extra_content` por mensaje

{
  "messages": [
    {
      "role": "...",
      "content": [
        { "type": "...", ..., "extra_content": { "google": { ... } } }
      ]
    }
}

`extra_content` por llamada a la herramienta

{
  "messages": [
    {
      "role": "...",
      "tool_calls": [
        {
          ...,
          "extra_content": { "google": { ... } }
        }
      ]
    }
  ]
}

Ejemplos de solicitudes de `curl`

Puedes usar estas solicitudes de curl directamente, en lugar de hacerlo a través del SDK.

Usa `thinking_config` con `extra_body`

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://us-central1-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/us-central1/endpoints/openapi/chat/completions \
  -d '{ \
    "model": "google/gemini-2.5-flash-preview-04-17", \
    "messages": [ \
      { "role": "user", \
      "content": [ \
        { "type": "text", \
          "text": "Are there any primes number of the form n*ceil(log(n))" \
        }] }], \
    "extra_body": { \
      "google": { \
          "thinking_config": { \
          "include_thoughts": true, "thinking_budget": 10000 \
        }, \
        "thought_tag_marker": "think" } }, \
    "stream": true }'

Utilizar `stream_function_call_arguments`

Solicitud de ejemplo:

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/global/endpoints/openapi/chat/completions \
  -d '{
  "model": "google/gemini-3-pro-preview", \
  "messages": [ \
    { "role": "user", "content": "What is the weather like in Boston and New Delhi today?" } ], \
  "tools": [ \
    { \
      "type": "function", \
      "function": { \
        "name": "get_current_weather", \
        "description": "Get the current weather in a given location", \
        "parameters": { \
          "type": "object", \
          "properties": { \
            "location": { \
              "type": "string", \
              "description": "The city and state, e.g. San Francisco, CA" \
            }, \
            "unit": { \
              "type": "string", \
              "enum": [ \
                "celsius", \
                "fahrenheit" \
              ] \
            } \
          }, \
          "required": [ \
            "location", \
            "unit" \
          ] \
        } \
      } \
    } \
  ], \
  "extra_body": { \
    "google": { \
      "stream_function_call_arguments": true \
    } \
  }, \
  "stream": true \
}'

Ejemplos de respuestas:

data: {"choices":[{"delta":{"role":"assistant","tool_calls":[{"extra_content":{"google":{"thought_signature":"..."}},"function":{"arguments":"","name":"get_current_weather"},"id":"function-call-c855348a-459a-46a4-a8ad-aa0a4e7c3563","index":1,"type":"function"}]},"index":0,"logprobs":null}],"created":1770850461,"id":"nQiNafGyF5rw998PstqooAY","model":"google/gemini-3-pro-preview","object":"chat.completion.chunk","system_fingerprint":""}

data: {"choices":[{"delta":{"role":"assistant","tool_calls":[{"function":{"arguments":"{\"location\":\"Boston, MA","name":"get_current_weather"},"id":"function-call-c855348a-459a-46a4-a8ad-aa0a4e7c3563","index":0,"type":"function"}]},"index":0,"logprobs":null}],"created":1770850461,"id":"nQiNafGyF5rw998PstqooAY","model":"google/gemini-3-pro-preview","object":"chat.completion.chunk","system_fingerprint":""}

data: {"choices":[{"delta":{"role":"assistant","tool_calls":[{"function":{"arguments":"\"","name":"get_current_weather"},"id":"function-call-c855348a-459a-46a4-a8ad-aa0a4e7c3563","index":0,"type":"function"}]},"index":0,"logprobs":null}],"created":1770850461,"id":"nQiNafGyF5rw998PstqooAY","model":"google/gemini-3-pro-preview","object":"chat.completion.chunk","system_fingerprint":""}

data: {"choices":[{"delta":{"role":"assistant","tool_calls":[{"function":{"arguments":",\"unit\":\"celsius","name":"get_current_weather"},"id":"function-call-c855348a-459a-46a4-a8ad-aa0a4e7c3563","index":0,"type":"function"}]},"index":0,"logprobs":null}],"created":1770850461,"id":"nQiNafGyF5rw998PstqooAY","model":"google/gemini-3-pro-preview","object":"chat.completion.chunk","system_fingerprint":""}

data: {"choices":[{"delta":{"role":"assistant","tool_calls":[{"function":{"arguments":"\"","name":"get_current_weather"},"id":"function-call-c855348a-459a-46a4-a8ad-aa0a4e7c3563","index":0,"type":"function"}]},"index":0,"logprobs":null}],"created":1770850461,"id":"nQiNafGyF5rw998PstqooAY","model":"google/gemini-3-pro-preview","object":"chat.completion.chunk","system_fingerprint":""}

data: {"choices":[{"delta":{"role":"assistant","tool_calls":[{"function":{"arguments":"}","name":"get_current_weather"},"id":"function-call-c855348a-459a-46a4-a8ad-aa0a4e7c3563","index":0,"type":"function"}]},"index":0,"logprobs":null}],"created":1770850461,"id":"nQiNafGyF5rw998PstqooAY","model":"google/gemini-3-pro-preview","object":"chat.completion.chunk","system_fingerprint":""}

data: {"choices":[{"delta":{"role":"assistant","tool_calls":[{"function":{"arguments":"","name":"get_current_weather"},"id":"function-call-df0d087c-ad74-46f1-ba4a-9353cbf288a8","index":0,"type":"function"}]},"index":0,"logprobs":null}],"created":1770850461,"id":"nQiNafGyF5rw998PstqooAY","model":"google/gemini-3-pro-preview","object":"chat.completion.chunk","system_fingerprint":""}

data: {"choices":[{"delta":{"role":"assistant","tool_calls":[{"function":{"arguments":"{\"location\":\"New Delhi, India","name":"get_current_weather"},"id":"function-call-df0d087c-ad74-46f1-ba4a-9353cbf288a8","index":1,"type":"function"}]},"index":0,"logprobs":null}],"created":1770850461,"id":"nQiNafGyF5rw998PstqooAY","model":"google/gemini-3-pro-preview","object":"chat.completion.chunk","system_fingerprint":""}

data: {"choices":[{"delta":{"role":"assistant","tool_calls":[{"function":{"arguments":"\"","name":"get_current_weather"},"id":"function-call-df0d087c-ad74-46f1-ba4a-9353cbf288a8","index":1,"type":"function"}]},"index":0,"logprobs":null}],"created":1770850461,"id":"nQiNafGyF5rw998PstqooAY","model":"google/gemini-3-pro-preview","object":"chat.completion.chunk","system_fingerprint":""}

data: {"choices":[{"delta":{"role":"assistant","tool_calls":[{"function":{"arguments":",\"unit\":\"celsius","name":"get_current_weather"},"id":"function-call-df0d087c-ad74-46f1-ba4a-9353cbf288a8","index":1,"type":"function"}]},"index":0,"logprobs":null}],"created":1770850461,"id":"nQiNafGyF5rw998PstqooAY","model":"google/gemini-3-pro-preview","object":"chat.completion.chunk","system_fingerprint":""}

data: {"choices":[{"delta":{"role":"assistant","tool_calls":[{"function":{"arguments":"\"","name":"get_current_weather"},"id":"function-call-df0d087c-ad74-46f1-ba4a-9353cbf288a8","index":1,"type":"function"}]},"index":0,"logprobs":null}],"created":1770850461,"id":"nQiNafGyF5rw998PstqooAY","model":"google/gemini-3-pro-preview","object":"chat.completion.chunk","system_fingerprint":""}

data: {"choices":[{"delta":{"role":"assistant","tool_calls":[{"function":{"arguments":"}","name":"get_current_weather"},"id":"function-call-df0d087c-ad74-46f1-ba4a-9353cbf288a8","index":1,"type":"function"}]},"finish_reason":"tool_calls","index":0,"logprobs":null}],"created":1770850461,"id":"nQiNafGyF5rw998PstqooAY","model":"google/gemini-3-pro-preview","object":"chat.completion.chunk","system_fingerprint":"","usage":{"completion_tokens":45,"completion_tokens_details":{"reasoning_tokens":504},"extra_properties":{"google":{"traffic_type":"PROVISIONED_THROUGHPUT"}},"prompt_tokens":27,"total_tokens":576}}

data: [DONE]

Generación de imágenes

Para seguir siendo compatible con el formato de respuesta de OpenAI, el campo audio de la respuesta se completa de forma explícita con un extra_content.google.mime_type que indica el tipo de MIME del resultado.

Solicitud de ejemplo:

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/global/endpoints/openapi/chat/completions \
  -d '{"model":"google/gemini-3-pro-image-preview", "messages":[{ "role": "user", "content": "Generate an image of a cat." }], "modalities": ["image"] }'

Respuesta de ejemplo:

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "message": {
        "audio": {
          "data": "<BASE64_BYTES>",
          "extra_content": {
            "google": {
              "mime_type": "image/png"
            }
          }
        },
        "content": null,
        "extra_content": {
          "google": {
            "thought_signature": "..."
          }
        },
        "role": "assistant"
      }
    }
  ],
  "created": 1770850692,
  "id": "hAmNaZb8BZOX4_UPlNXoEA",
  "model": "google/gemini-3-pro-image-preview",
  "object": "chat.completion",
  "system_fingerprint": "",
  "usage": {
    "completion_tokens": 1120,
    "completion_tokens_details": {
      "reasoning_tokens": 251
    },
    "extra_properties": {
      "google": {
        "traffic_type": "PROVISIONED_THROUGHPUT"
      }
    },
    "prompt_tokens": 7,
    "total_tokens": 1378
  }
}

Solicitudes multimodales

La API de Chat Completions admite una variedad de entradas multimodales, incluido audio y video.

Usa `image_url` para pasar datos de imágenes

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://us-central1-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/us-central1/endpoints/openapi/chat/completions \
  -d '{ \
    "model": "google/gemini-2.0-flash-001", \
    "messages": [{ "role": "user", "content": [ \
      { "type": "text", "text": "Describe this image" }, \
      { "type": "image_url", "image_url": "gs://cloud-samples-data/generative-ai/image/scones.jpg" }] }] }'

Usa `input_audio` para pasar datos de audio

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://us-central1-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/us-central1/endpoints/openapi/chat/completions \
  -d '{ \
    "model": "google/gemini-2.0-flash-001", \
    "messages": [ \
      { "role": "user", \
        "content": [ \
          { "type": "text", "text": "Describe this: " }, \
          { "type": "input_audio", "input_audio": { \
            "format": "audio/mp3", \
            "data": "gs://cloud-samples-data/generative-ai/audio/pixel.mp3" } }] }] }'

Respuestas de funciones multimodales

Solicitud de ejemplo:

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/global/endpoints/openapi/chat/completions \
  -d '{ \
    "model": "google/gemini-3-pro-preview", \
    "messages": [ \
      { "role": "user", "content": "Show me the green shirt I ordered last month." }, \
      { \
        "role": "assistant", \
        "tool_calls": [ \
          { \
            "extra_content": { \
              "google": { \
                "thought_signature": "<THOUGHT_SIGNATURE>" \
              } \
            }, \
            "function": { \
              "arguments": "{\"item_name\":\"green shirt\"}", \
              "name": "get_image" \
            }, \
            "id": "function-call-a350228d-0283-4792-8bfa-40da064fb959", \
            "type": "function" \
          } \
        ] \
      }, \
      { \
        "role": "tool", \
        "tool_call_id": "function-call-a350228d-0283-4792-8bfa-40da064fb959", \
        "content": "{\"image_ref\":{\"$ref\":\"dress.jpg\"}}", \
        "extra_content": { \
          "google": { \
            "parts": [ \
              { \
                "file_data": { \
                  "mime_type": "image/jpg", \
                  "display_name": "dress.jpg", \
                  "file_uri": "gs://cloud-samples-data/generative-ai/image/dress.jpg" \
                } \
              } \
            ] \
          } \
        } \
      } \
    ], \
    "tools": [ \
      { \
        "type": "function", \
        "function": { \
          "name": "get_image", \
          "description": "Retrieves the image file reference for a specific order item.", \
          "parameters": { \
            "type": "object", \
            "properties": { \
              "item_name": { \
                "type": "string", \
                "description": "The name or description of the item ordered (e.g., 'green shirt')." \
              } \
            }, \
            "required": [ \
              "item_name" \
            ] \
          } \
        } \
      } \
    ] \
  }'

Respuesta de ejemplo:

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "message": {
        "content": "Here is the image of the green shirt you ordered.",
        "role": "assistant"
      }
    }
  ],
  "created": 1770852204,
  "id": "bA-NacCPKoae_9MPsNCn6Qc",
  "model": "google/gemini-3-pro-preview",
  "object": "chat.completion",
  "system_fingerprint": "",
  "usage": {
    "completion_tokens": 16,
    "extra_properties": {
      "google": {
        "traffic_type": "ON_DEMAND"
      }
    },
    "prompt_tokens": 1139,
    "total_tokens": 1155
  }
}

Resultados estructurados

Puedes usar el parámetro response_format para obtener un resultado estructurado.

Ejemplo de uso del SDK

from pydantic import BaseModel
from openai import OpenAI

client = OpenAI()

class CalendarEvent(BaseModel):
    name: str
    date: str
    participants: list[str]

completion = client.beta.chat.completions.parse(
    model="google/gemini-2.5-flash-preview-04-17",
    messages=[
        {"role": "system", "content": "Extract the event information."},
        {"role": "user", "content": "Alice and Bob are going to a science fair on Friday."},
    ],
    response_format=CalendarEvent,
)

print(completion.choices[0].message.parsed)

Usa el endpoint global en el modo compatible con OpenAI

En el siguiente ejemplo, se muestra cómo usar el endpoint global en el modo compatible con OpenAI:

REST

  curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/global/endpoints/openapi/chat/completions\
  -d '{ \
    "model": "google/gemini-2.0-flash-001", \
    "messages": [ \
    {"role": "user", \
      "content": "Hello World" \
      }] \
      }'

¿Qué sigue?

Para ver ejemplos de cómo llamar a la API de Inference con la sintaxis compatible con OpenAI.
Para ver ejemplos de cómo llamar a la API de Functions Calling con una sintaxis compatible con OpenAI.
Obtén más información sobre la API de Gemini.
Obtén más información para migrar de Azure OpenAI a la API de Gemini.

Ejemplos Organiza tus páginas con colecciones Guarda y categoriza el contenido según tus preferencias.

Llama a Gemini con la API de Chat Completions

REST

Python

REST

Python

Envía una instrucción y una imagen a la API de Gemini en Agent Platform de Gemini Enterprise

Python

Llama a un modelo que se implementó por sí solo con la API de Chat Completions

REST

Python

REST

Python

extra_body ejemplos

Agregar thought_tag_marker

Agrega extra_body con el SDK

extra_content ejemplos

extra_content con la cadena content

extra_content por mensaje

extra_content por llamada a la herramienta

Ejemplos de solicitudes de curl

Usa thinking_config con extra_body

Utilizar stream_function_call_arguments

Generación de imágenes

Solicitudes multimodales

Usa image_url para pasar datos de imágenes

Usa input_audio para pasar datos de audio

Respuestas de funciones multimodales

Resultados estructurados

Ejemplo de uso del SDK

Usa el endpoint global en el modo compatible con OpenAI

REST

¿Qué sigue?

Ejemplos

`extra_body` ejemplos

Agregar `thought_tag_marker`

Agrega `extra_body` con el SDK

`extra_content` ejemplos

`extra_content` con la cadena `content`

`extra_content` por mensaje

`extra_content` por llamada a la herramienta

Ejemplos de solicitudes de `curl`

Usa `thinking_config` con `extra_body`

Utilizar `stream_function_call_arguments`

Usa `image_url` para pasar datos de imágenes

Usa `input_audio` para pasar datos de audio