Images

Generate images using Gemini’s native image generation capabilities.

Endpoint

POST https://api.scalellm.dev/v1beta/models/gemini-3-pro-image-preview:generateContent

Examples

Python
JavaScript
cURL

import google.generativeai as genai
import base64

genai.configure(
    api_key="sk_your_key",
    transport="rest",
    client_options={"api_endpoint": "api.scalellm.dev"}
)

model = genai.GenerativeModel("gemini-3-pro-image-preview")

response = model.generate_content("Create a picture of a futuristic city at sunset")

# Save the generated image
for part in response.candidates[0].content.parts:
    if hasattr(part, 'inline_data'):
        image_data = base64.b64decode(part.inline_data.data)
        with open("generated-image.png", "wb") as f:
            f.write(image_data)

import { GoogleGenerativeAI } from '@google/generative-ai';
import * as fs from 'fs';

const genAI = new GoogleGenerativeAI('sk_your_key', {
  baseUrl: 'https://api.scalellm.dev'
});

const model = genAI.getGenerativeModel({ model: 'gemini-3-pro-image-preview' });

const result = await model.generateContent(
  'Create a picture of a futuristic city at sunset'
);

// Save the generated image
const parts = result.response.candidates[0].content.parts;
for (const part of parts) {
  if (part.inlineData) {
    const imageBuffer = Buffer.from(part.inlineData.data, 'base64');
    fs.writeFileSync('generated-image.png', imageBuffer);
  }
}

curl -s https://api.scalellm.dev/v1beta/models/gemini-3-pro-image-preview:generateContent \
  -H "x-goog-api-key: sk_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [
        {"text": "Create a picture of a futuristic city at sunset"}
      ]
    }]
  }' \
  | grep -o '"data": "[^"]*"' \
  | cut -d'"' -f4 \
  | base64 --decode > generated-image.png

Request Body

Parameter	Type	Required	Description
`contents`	array	Yes	Array of content objects
`generationConfig`	object	No	Generation configuration

Content Object

Field	Type	Description
`parts`	array	Array of part objects with text prompt

Part Object

Field	Type	Description
`text`	string	Image generation prompt

Response

The response includes base64-encoded image data:

{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "iVBORw0KGgoAAAANSUhEUgAA..."
            }
          }
        ],
        "role": "model"
      },
      "finishReason": "STOP"
    }
  ]
}

Response Fields

Field	Type	Description
`candidates`	array	Array of generated candidates
`candidates[].content.parts[].inlineData.mimeType`	string	Image MIME type (e.g., `image/png`)
`candidates[].content.parts[].inlineData.data`	string	Base64-encoded image data
`candidates[].finishReason`	string	Why generation stopped

More Examples

Artistic Image

Python
JavaScript
cURL

import google.generativeai as genai
import base64

genai.configure(
    api_key="sk_your_key",
    transport="rest",
    client_options={"api_endpoint": "api.scalellm.dev"}
)

model = genai.GenerativeModel("gemini-3-pro-image-preview")

response = model.generate_content(
    "An oil painting of a serene mountain landscape at dawn"
)

for part in response.candidates[0].content.parts:
    if hasattr(part, 'inline_data'):
        image_data = base64.b64decode(part.inline_data.data)
        with open("landscape.png", "wb") as f:
            f.write(image_data)

import { GoogleGenerativeAI } from '@google/generative-ai';
import * as fs from 'fs';

const genAI = new GoogleGenerativeAI('sk_your_key', {
  baseUrl: 'https://api.scalellm.dev'
});

const model = genAI.getGenerativeModel({ model: 'gemini-3-pro-image-preview' });

const result = await model.generateContent(
  'An oil painting of a serene mountain landscape at dawn'
);

const parts = result.response.candidates[0].content.parts;
for (const part of parts) {
  if (part.inlineData) {
    fs.writeFileSync('landscape.png', Buffer.from(part.inlineData.data, 'base64'));
  }
}

curl -s https://api.scalellm.dev/v1beta/models/gemini-3-pro-image-preview:generateContent \
  -H "x-goog-api-key: sk_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [
        {"text": "An oil painting of a serene mountain landscape at dawn"}
      ]
    }]
  }' \
  | grep -o '"data": "[^"]*"' \
  | cut -d'"' -f4 \
  | base64 --decode > landscape.png

Product Visualization

Python
JavaScript
cURL

import google.generativeai as genai
import base64

genai.configure(
    api_key="sk_your_key",
    transport="rest",
    client_options={"api_endpoint": "api.scalellm.dev"}
)

model = genai.GenerativeModel("gemini-3-pro-image-preview")

response = model.generate_content(
    "A sleek smartphone on a minimalist white desk, product photography"
)

for part in response.candidates[0].content.parts:
    if hasattr(part, 'inline_data'):
        image_data = base64.b64decode(part.inline_data.data)
        with open("product.png", "wb") as f:
            f.write(image_data)

import { GoogleGenerativeAI } from '@google/generative-ai';
import * as fs from 'fs';

const genAI = new GoogleGenerativeAI('sk_your_key', {
  baseUrl: 'https://api.scalellm.dev'
});

const model = genAI.getGenerativeModel({ model: 'gemini-3-pro-image-preview' });

const result = await model.generateContent(
  'A sleek smartphone on a minimalist white desk, product photography'
);

const parts = result.response.candidates[0].content.parts;
for (const part of parts) {
  if (part.inlineData) {
    fs.writeFileSync('product.png', Buffer.from(part.inlineData.data, 'base64'));
  }
}

curl -s https://api.scalellm.dev/v1beta/models/gemini-3-pro-image-preview:generateContent \
  -H "x-goog-api-key: sk_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [
        {"text": "A sleek smartphone on a minimalist white desk, product photography"}
      ]
    }]
  }' \
  | grep -o '"data": "[^"]*"' \
  | cut -d'"' -f4 \
  | base64 --decode > product.png

Available Models

Model	Description
`gemini-3-pro-image-preview`	Multimodal with native image generation

Headers

Header	Required	Description
`x-goog-api-key`	Yes	Your ScaleLLM API key (`sk_your_key`)
`Content-Type`	Yes	`application/json`

For text generation and vision tasks, see the Chat endpoint.

OpenAI Compatible

Anthropic Compatible

Google Compatible

Reference

Images

Images

Endpoint

Examples

Request Body

Content Object

Part Object

Response

Response Fields

More Examples

Artistic Image

Product Visualization

Available Models

Headers

OpenAI Compatible

Anthropic Compatible

Google Compatible

Reference

​Images

​Endpoint

​Examples

​Request Body

​Content Object

​Part Object

​Response

​Response Fields

​More Examples

​Artistic Image

​Product Visualization

​Available Models

​Headers

Images

Endpoint

Examples

Request Body

Content Object

Part Object

Response

Response Fields

More Examples

Artistic Image

Product Visualization

Available Models

Headers