Gemini Developer API vs. Gemini platform

When developing generative AI solutions with Gemini, Google offers two API products: the Gemini Developer API and the Gemini platform API.

The Gemini Developer API provides the fastest path to build, productionize, and scale Gemini powered applications. Most developers should use the Gemini Developer API unless there is a need for specific enterprise controls.

Gemini platform offers a comprehensive ecosystem of enterprise ready features and services for building and deploying generative AI applications backed by Google Cloud.

We've recently simplified migrating between these services. Both the Gemini Developer API and the Gemini platform API are now accessible through the unified Google GenAI SDK and the Interactions API.

Code comparison: Interactions API (recommended)

The Interactions API is the recommended way to build with Gemini models and agents. The following examples compare text generation between the Gemini Developer API and Gemini platform.

Python

You can access both the Gemini Developer API and Gemini platform services through the google-genai library (>= 2.3.0). See the libraries page for instructions on how to install google-genai.

Gemini Developer API

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input="Explain how AI works in a few words",
)
print(interaction.output_text)

Gemini platform API

from google import genai

client = genai.Client(
    enterprise=True, project="your-project-id", location="global"
)

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input="Explain how AI works in a few words",
)
print(interaction.output_text)

JavaScript and TypeScript

You can access both Gemini Developer API and Gemini platform services through the @google/genai library (>= 2.3.0). See the libraries page for instructions on how to install @google/genai.

Gemini Developer API

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

const interaction = await ai.interactions.create({
  model: "gemini-3.8-flash",
  input: "Explain how AI works in a few words",
});
console.log(interaction.output_text);

Gemini platform API

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  enterprise: true,
  project: "your_project",
  location: "global",
});

const interaction = await ai.interactions.create({
  model: "gemini-3.8-flash",
  input: "Explain how AI works in a few words",
});
console.log(interaction.output_text);

Code comparison: generateContent API

While the Interactions API is recommended for new projects, the generateContent API remains supported.

Python

You can access both the Gemini Developer API and Gemini platform services through the google-genai library. See the libraries page for instructions on how to install google-genai.

Gemini Developer API

from google import genai

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3.8-flash", contents="Explain how AI works in a few words"
)
print(response.text)

Gemini platform API

from google import genai

client = genai.Client(
    vertexai=True, project='your-project-id', location='us-central1'
)

response = client.models.generate_content(
    model="gemini-3.8-flash", contents="Explain how AI works in a few words"
)
print(response.text)

JavaScript and TypeScript

You can access both Gemini Developer API and Gemini platform services through @google/genai library. See libraries page for instructions on how to install @google/genai.

Gemini Developer API

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const response = await ai.models.generateContent({
    model: "gemini-3.8-flash",
    contents: "Explain how AI works in a few words",
  });
  console.log(response.text);
}

main();

Gemini platform API

import { GoogleGenAI } from '@google/genai';
const ai = new GoogleGenAI({
  vertexai: true,
  project: 'your_project',
  location: 'your_location',
});

async function main() {
  const response = await ai.models.generateContent({
    model: "gemini-3.8-flash",
    contents: "Explain how AI works in a few words",
  });
  console.log(response.text);
}

main();

Go

You can access both Gemini Developer API and Gemini platform services through google.golang.org/genai library. See libraries page for instructions on how to install google.golang.org/genai.

Gemini Developer API

import (
  "context"
  "encoding/json"
  "fmt"
  "log"
  "google.golang.org/genai"
)

// Your Google API key
const apiKey = "your-api-key"

func main() {
  ctx := context.Background()
  client, err := genai.NewClient(ctx, nil)
  if err != nil {
      log.Fatal(err)
  }

  // Call the GenerateContent method.
  result, err := client.Models.GenerateContent(ctx, "gemini-3.8-flash", genai.Text("Tell me about New York?"), nil)

}

Gemini platform API

import (
  "context"
  "encoding/json"
  "fmt"
  "log"
  "google.golang.org/genai"
)

// Your Google Cloud project
const project = "your-project"

// A Google Cloud location like "us-central1"
const location = "some-gcp-location"

func main() {
  ctx := context.Background()
  client, err := genai.NewClient(ctx, &genai.ClientConfig
  {
        Project:  project,
      Location: location,
      Backend:  genai.BackendVertexAI,
  })

  // Call the GenerateContent method.
  result, err := client.Models.GenerateContent(ctx, "gemini-3.8-flash", genai.Text("Tell me about New York?"), nil)

}

Other use cases and platforms

Refer to use case specific guides on Gemini Developer API Documentation and Gemini platform documentation for other platforms and use cases.

Migration considerations

When you migrate:

If you no longer need to use your Gemini API key for the Gemini Developer API, then follow security best practices and delete it.

To delete an API key:

  1. Open the Google Cloud API Credentials page.

  2. Find the API key you want to delete and click the Actions icon.

  3. Select Delete API key.

  4. In the Delete credential modal, select Delete.

    Deleting an API key takes a few minutes to propagate. After propagation completes, any traffic using the deleted API key is rejected.

Next steps