Responses API

OpenAI partner models on Gemini Enterprise Agent Platform support the OpenAI Responses API (publishers/openai/v1/responses) for text generation from text and image inputs, tool calling, reasoning effort control, and conversation compaction.

Before you begin

To use OpenAI partner models with Gemini Enterprise Agent Platform, you must complete the following steps. The Gemini Enterprise Agent Platform API (aiplatform.googleapis.com) must be enabled on your Cloud de Confiance project.

1. In the Cloud de Confiance console, on the project selector page, select or create a Cloud de Confiance project.

   Roles required to select or create a project

   • Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
   • Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

   Go to project selector

2. Verify that billing is enabled for your Cloud de Confiance project.

3. Enable the Gemini Enterprise Agent Platform API, if it is not already enabled.

   Roles required to enable APIs

   To enable APIs, you need the serviceusage.services.enable permission. If you created the project, then you likely already have this permission through the Owner role (roles/owner). Otherwise, you can get this permission through the Service Usage Admin role (roles/serviceusage.serviceUsageAdmin). Learn how to grant roles.

   Enable the API

4. Complete the onboarding steps in OpenAI GPT Models, including purchasing the product through Google Cloud Marketplace and enabling the model in Model Garden.

5. If your organization's policy restricts model access, allow the model in that policy.

Required roles

To get the permissions that you need to call OpenAI partner models, ask your administrator to grant you the Agent Platform User (roles/aiplatform.user) IAM role on the project. For more information about granting roles, see Manage access to projects, folders, and organizations.

You might also be able to get the required permissions through custom roles or other predefined roles.

Endpoints

OpenAI partner models are served from the following Agent Platform base URLs:

• Global endpoint (global): https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/publishers/openai/v1
• US multi-region endpoint (us): https://aiplatform.us.rep.googleapis.com/v1/projects/PROJECT_ID/locations/us/publishers/openai/v1

Replace <var>PROJECT_ID</var> with your Cloud de Confiance project ID.

Call the Responses API using the OpenAI Python SDK

You can use the official openai Python library by setting base_url to your Agent Platform endpoint and passing a refreshed Cloud de Confiance by S3NS OAuth 2.0 access token as api_key. Set store=False for stateless requests and ZDR workloads.

import google.auth
from google.auth.transport.requests import Request
from openai import OpenAI

credentials, _ = google.auth.default(
    scopes=["https://www.googleapis.com/auth/cloud-platform"]
)
credentials.refresh(Request())

project_id = "PROJECT_ID"
base_url = (
    f"https://aiplatform.googleapis.com/v1/projects/{project_id}"
    "/locations/global/publishers/openai/v1"
)

client = OpenAI(
    base_url=base_url,
    api_key=credentials.token,
)

response = client.responses.create(
    model="gpt-6.1-sol",
    input="Explain how Zero Data Retention works on Agent Platform.",
    reasoning={"effort": "medium"},
    store=False,
)
print(response.output_text)

Stream responses

To stream incremental text deltas over server-sent events (SSE), set stream=True:

import google.auth
from google.auth.transport.requests import Request
from openai import OpenAI

credentials, _ = google.auth.default(
    scopes=["https://www.googleapis.com/auth/cloud-platform"]
)
credentials.refresh(Request())

project_id = "PROJECT_ID"
base_url = (
    f"https://aiplatform.googleapis.com/v1/projects/{project_id}"
    "/locations/global/publishers/openai/v1"
)

client = OpenAI(
    base_url=base_url,
    api_key=credentials.token,
)

stream = client.responses.create(
    model="gpt-6-luna",
    input="Write a short Python function to validate a JSON schema.",
    stream=True,
    store=False,
)

for event in stream:
    if event.type == "response.output_text.delta":
        print(event.delta, end="")

Compact conversation history

For long-horizon agentic sessions, call the standalone compaction endpoint (POST .../responses/compact) to compress prior messages into an encrypted compaction item that can be passed into subsequent stateless /responses calls:

import google.auth
from google.auth.transport.requests import Request
from openai import OpenAI

credentials, _ = google.auth.default(
    scopes=["https://www.googleapis.com/auth/cloud-platform"]
)
credentials.refresh(Request())

project_id = "PROJECT_ID"
base_url = (
    f"https://aiplatform.googleapis.com/v1/projects/{project_id}"
    "/locations/global/publishers/openai/v1"
)

client = OpenAI(
    base_url=base_url,
    api_key=credentials.token,
)

compacted = client.responses.compact(
    model="gpt-6-astra",
    input=[
        {"role": "user", "content": "Audit our multi-region VPC firewall rules."},
        {"role": "assistant", "content": "I checked the ingress rules for us-east1 and us-central1."},
    ],
)
print(compacted.output)

Call the Responses API using the OpenAI Node.js SDK

You can use the official openai Node.js library with Cloud de Confiance by S3NS OAuth credentials:

import OpenAI from "openai";

const projectId = "PROJECT_ID";
const client = new OpenAI({
  apiKey: process.env.GOOGLE_CLOUD_ACCESS_TOKEN,
  baseURL: `https://aiplatform.googleapis.com/v1/projects/${projectId}/locations/global/publishers/openai/v1`,
});

const response = await client.responses.create({
  model: "gpt-6-luna",
  input: "Write a short summary of how authentication works on Agent Platform.",
  store: false,
});
console.log(response.output_text);

Call the Responses API using the OpenAI Go SDK

You can use the official openai-go library with Cloud de Confiance by S3NS OAuth credentials:

package main

import (
    "context"
    "fmt"
    "os"

    "github.com/openai/openai-go/v3"
    "github.com/openai/openai-go/v3/option"
    "github.com/openai/openai-go/v3/responses"
)

func main() {
    ctx := context.Background()
    projectID := "PROJECT_ID"
    client := openai.NewClient(
        option.WithAPIKey(os.Getenv("GOOGLE_CLOUD_ACCESS_TOKEN")),
        option.WithBaseURL("https://aiplatform.googleapis.com/v1/projects/"+projectID+"/locations/global/publishers/openai/v1"),
    )

    response, err := client.Responses.New(ctx, responses.ResponseNewParams{
        Model: "gpt-6-luna",
        Input: responses.ResponseNewParamsInputUnion{
            OfString: openai.String("Write a one-sentence bedtime story about a unicorn."),
        },
        Store: openai.Bool(false),
    })
    if err != nil {
        panic(err)
    }
    fmt.Println(response.OutputText())
}

Call the Responses API using curl

You can send a REST request directly to the Responses API using curl.

Before using any of the request data, make the following replacements:

• PROJECT_ID: Your Cloud de Confiance project ID.

HTTP method and URL:

POST https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/publishers/openai/v1/responses

Request JSON body:

{
  "model": "gpt-6.1-sol",
  "input": "Summarize the key differences between Cloud de Confiance by S3NS and OpenAI terms.",
  "reasoning": {"effort": "medium"},
  "store": false
}

To send your request, expand one of these options:

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/publishers/openai/v1/responses"

$cred = gcloud auth application-default 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/publishers/openai/v1/responses" | Select-Object -Expand Content

You should receive a successful status code (2xx) and an empty response.

Error handling

Build exponential backoff with jitter on 429 and 5xx responses into production workloads.

Connect Codex to Cloud de Confiance by S3NS

You can configure OpenAI Codex (CLI or Desktop App) to route model requests through your Cloud de Confiance project using Cloud de Confiance by S3NS authentication. For complete setup instructions, interactive sign-in steps, and manual config.toml options, see Connect OpenAI Codex to Cloud de Confiance by S3NS.

What's next

• Configure developer tools in Connect OpenAI Codex to Cloud de Confiance by S3NS.
• Review model specifications, ZDR procedures, and governing terms in OpenAI GPT Models.
• Learn about Abuse monitoring and Zero data retention.