Beispiele

Gemini mit der Chat Completions API aufrufen

Im folgenden Beispiel wird gezeigt, wie Nicht-Streaming Anfragen gesendet werden:

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

Folgen Sie der Anleitung für die Einrichtung von Python in der Kurzanleitung zur Agent Platform mit Clientbibliotheken, bevor Sie dieses Beispiel anwenden. Weitere Informationen finden Sie in der APIPython Referenzdokumentation zur Agent Platform.

Richten Sie die Standardanmeldedaten für Anwendungen ein, um sich bei der Agent Platform zu authentifizieren. Weitere Informationen finden Sie unter Authentifizierung für eine lokale Entwicklungsumgebung einrichten. 

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)

Im folgenden Beispiel wird gezeigt, wie Sie mit der Chat Completions API Streaminganfragen an ein Gemini-Modell senden:

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

Folgen Sie der Anleitung für die Einrichtung von Python in der Kurzanleitung zur Agent Platform mit Clientbibliotheken, bevor Sie dieses Beispiel anwenden. Weitere Informationen finden Sie in der APIPython Referenzdokumentation zur Agent Platform.

Richten Sie die Standardanmeldedaten für Anwendungen ein, um sich bei der Agent Platform zu authentifizieren. Weitere Informationen finden Sie unter Authentifizierung für eine lokale Entwicklungsumgebung einrichten. 

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)

Einen Prompt und ein Bild an die Gemini API in der Gemini Enterprise Agent Platform senden

Python

Folgen Sie der Anleitung für die Einrichtung von Python in der Kurzanleitung zur Agent Platform mit Clientbibliotheken, bevor Sie dieses Beispiel anwenden. Weitere Informationen finden Sie in der APIPython Referenzdokumentation zur Agent Platform.

Richten Sie die Standardanmeldedaten für Anwendungen ein, um sich bei der Agent Platform zu authentifizieren. Weitere Informationen finden Sie unter Authentifizierung für eine lokale Entwicklungsumgebung einrichten. 


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)

Ein selbst bereitgestelltes Modell mit der Chat Completions API aufrufen

Im folgenden Beispiel wird gezeigt, wie Nicht-Streaming Anfragen gesendet werden:

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

Folgen Sie der Anleitung für die Einrichtung von Python in der Kurzanleitung zur Agent Platform mit Clientbibliotheken, bevor Sie dieses Beispiel anwenden. Weitere Informationen finden Sie in der APIPython Referenzdokumentation zur Agent Platform.

Richten Sie die Standardanmeldedaten für Anwendungen ein, um sich bei der Agent Platform zu authentifizieren. Weitere Informationen finden Sie unter Authentifizierung für eine lokale Entwicklungsumgebung einrichten. 

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)

Im folgenden Beispiel wird gezeigt, wie Sie mit der Chat Completions API Streaminganfragen an ein selbst bereitgestelltes Modell senden:

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

Folgen Sie der Anleitung für die Einrichtung von Python in der Kurzanleitung zur Agent Platform mit Clientbibliotheken, bevor Sie dieses Beispiel anwenden. Weitere Informationen finden Sie in der APIPython Referenzdokumentation zur Agent Platform.

Richten Sie die Standardanmeldedaten für Anwendungen ein, um sich bei der Agent Platform zu authentifizieren. Weitere Informationen finden Sie unter Authentifizierung für eine lokale Entwicklungsumgebung einrichten. 

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)

Beispiele für extra_body

Sie können entweder das SDK oder die REST API verwenden, um extra_body zu übergeben.

thought_tag_marker hinzufügen

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

extra_body mit dem SDK hinzufügen

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

Beispiele für extra_content

Sie können dieses Feld direkt mit der REST API ausfüllen.

extra_content mit String content

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

extra_content pro Nachricht

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

extra_content pro Toolaufruf

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

Beispielanfragen mit curl

Sie können diese curl-Anfragen direkt verwenden, ohne das SDK zu verwenden.

thinking_config mit extra_body verwenden

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 }'

stream_function_call_arguments verwenden

Beispielanfrage:

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 \
}'

Beispielantworten:

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]

Bildgenerierung

Um mit dem OpenAI-Antwortformat kompatibel zu bleiben, wird das Feld audio der Antwort explizit mit einem extra_content.google.mime_type gefüllt, der den MIME-Typ des Ergebnisses angibt.

Beispielanfrage:

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"] }'

Beispielantwort:

{
  "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
  }
}

Multimodale Anfragen

Die Chat Completions API unterstützt eine Vielzahl multimodaler Eingaben, einschließlich Audio und Video.

image_url verwenden, um Bilddaten zu übergeben

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" }] }] }'

input_audio verwenden, um Audiodaten zu übergeben

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" } }] }] }'

Multimodale Funktionsantworten

Beispielanfrage:

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" \
            ] \
          } \
        } \
      } \
    ] \
  }'

Beispielantwort:

{
  "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
  }
}

Strukturierte Ausgabe

Mit dem Parameter response_format können Sie eine strukturierte Ausgabe erhalten.

Beispiel mit dem 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)

Globalen Endpunkt im OpenAI-kompatiblen Modus verwenden

Im folgenden Beispiel wird gezeigt, wie Sie den globalen Endpunkt im OpenAI-kompatiblen Modus verwenden:

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" \
      }] \
      }'

Nächste Schritte