Name: Gemini 3 Pro Image API
Brand: Google

Overview

What is Gemini 3 Pro Image API?

Gemini 3 Pro Image is a text-to-image model that generates images from text descriptions.

Technical Specifications
- Supported inputs: Image, Text
- Output: Image
- Endpoint: /images/generations

Performance Benchmarks
[embed]

Gemini 3 Pro Image API Pricing
- Input: $0 / 1M tokens
- Output: $0 / 1M tokens
- Output images: $0 / 1M tokens

Where to Use Gemini 3 Pro Image

High-volume image generation
Produce product visuals, thumbnails, and marketing assets programmatically at scale.

Creative and concept art
Turn text prompts into illustrations, mockups, and design explorations.

Image editing and variations
Provide a reference image to guide edits, restyles, or variations.

Code Sample
[embed]

Uptime and performance

Uptime (24h): 100%
Uptime (7d): 100%
Availability (24h): 100%
Error rate (24h): 0%

Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.

Use cases

Gemini 3 Pro Image Preview is documented as suited to complex scene composition, typography-heavy designs, and natural language-driven editing.

It is also documented for creating and editing images with studio-quality precision and control, including testing ideas, creating eye-catching designs, and mocking up prototypes.

Google’s developer documentation says it is best for complex graphic projects, high-fidelity product mockups, and fact-based data visualizations that require accurate text rendering and real-world grounding.

It is also described as useful for turning notes into diagrams and for visualizing ideas and designing anything from prototypes to infographics.

How to use Gemini 3 Pro Image API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to google/gemini-3-pro-image-preview.

import requests

r = requests.post(
    "https://api.aimlapi.com/v1/images/generations",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "google/gemini-3-pro-image-preview",
      "prompt": "A cat holding a sign that says hello"
    },
)
print(r.json())

const r = await fetch("https://api.aimlapi.com/v1/images/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "google/gemini-3-pro-image-preview",
    "prompt": "A cat holding a sign that says hello"
  }),
});
console.log(await r.json());

curl -X POST https://api.aimlapi.com/v1/images/generations \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-3-pro-image-preview","prompt":"A cat holding a sign that says hello"}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.