Examples

Call Gemini with the Chat Completions API

The following sample shows you how to send non-streaming requests:

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

Before trying this sample, follow the Python setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Python API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment. 

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)

The following sample shows you how to send streaming requests to a Gemini model by using the Chat Completions API:

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

Before trying this sample, follow the Python setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Python API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment. 

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)

Send a prompt and an image to the Gemini API in Vertex AI

Python

Before trying this sample, follow the Python setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Python API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment. 


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)

Call a self-deployed model with the Chat Completions API

The following sample shows you how to send non-streaming requests:

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

Before trying this sample, follow the Python setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Python API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment. 

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)

The following sample shows you how to send streaming requests to a self-deployed model by using the Chat Completions API:

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

Before trying this sample, follow the Python setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Python API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment. 

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 examples

You can use either the SDK or the REST API to pass in extra_body.

Add thought_tag_marker

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

Add extra_body using the SDK

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

extra_content examples

You can populate this field by using the REST API directly.

extra_content with string content

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

Per-message extra_content

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

Per-tool call extra_content

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

Sample curl requests

You can use these curl requests directly, rather than going through the SDK.

Use thinking_config with 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 }'

Multimodal requests

The Chat Completions API supports a variety of multimodal input, including both audio and video.

Use image_url to pass in image data

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}/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" }] }] }'

Use input_audio to pass in audio data

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}/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" } }] }] }'

Structured output

You can use the response_format parameter to get structured output.

Example using 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)

What's next