GoogleImage generationReleased November 20, 2025

Gemini 3 Pro Image (Preview)

Name: Gemini 3 Pro Image (Preview)
Brand: Google
SKU: gemini-3-pro-image-preview
Availability: InStock

Gemini 3 Pro Image (Preview) costs $2 per 1M input tokens and $120 per 1M output tokens on LLM API, with a 66K-token context window.

Pricing

Lowest price among 2 providers, after discounts.

Gemini 3 Pro Image (Preview) prices on LLM API
Input	$2	per 1M tokens
Output	$120	per 1M tokens
Cache read	$0.2	per 1M tokens

Providers

Prices after each provider’s discount; the lowest in bold.

Sort

Providers of Gemini 3 Pro Image (Preview) on LLM API

Google AI Studio	$2	$120	$0.2
Google Vertex AI	$2	$120	$0.2

Specifications

ModesGenerate, Edit
Output formatsPNG
Input imagesUp to 14, 20 MB each
Sizes10 sizes
- 1024×1024
- 848×1264
- 1264×848
- 896×1200
- 1200×896
- 928×1152
- 1152×928
- 768×1376
- 1376×768
- 1584×672

Call Gemini 3 Pro Image (Preview)

POST /v1/images/generationsSet LLMAPI_KEY to your LLM API key.Generate docs

import base64
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

result = client.images.generate(
    model="gemini-3-pro-image-preview",
    prompt="A lighthouse at dawn, watercolor",
)
with open(f"image.{result.output_format}", "wb") as f:
    f.write(base64.b64decode(result.data[0].b64_json))

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.llmapi.ai/v1",
  apiKey: process.env.LLMAPI_KEY,
});

const result = await client.images.generate({
  model: "gemini-3-pro-image-preview",
  prompt: "A lighthouse at dawn, watercolor",
});
fs.writeFileSync(`image.${result.output_format}`, Buffer.from(result.data![0].b64_json!, "base64"));

curl https://api.llmapi.ai/v1/images/generations \
  -H "Authorization: Bearer $LLMAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-pro-image-preview",
    "prompt": "A lighthouse at dawn, watercolor"
  }'

POST /v1/images/editsSet LLMAPI_KEY to your LLM API key.Edit docs

import base64
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

result = client.images.edit(
    model="gemini-3-pro-image-preview",
    image=open("photo.png", "rb"),
    prompt="Replace the sky with a sunset",
)
with open(f"edited.{result.output_format}", "wb") as f:
    f.write(base64.b64decode(result.data[0].b64_json))

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.llmapi.ai/v1",
  apiKey: process.env.LLMAPI_KEY,
});

const result = await client.images.edit({
  model: "gemini-3-pro-image-preview",
  image: fs.createReadStream("photo.png"),
  prompt: "Replace the sky with a sunset",
});
fs.writeFileSync(`edited.${result.output_format}`, Buffer.from(result.data![0].b64_json!, "base64"));

curl https://api.llmapi.ai/v1/images/edits \
  -H "Authorization: Bearer $LLMAPI_KEY" \
  -F model="gemini-3-pro-image-preview" \
  -F image="@photo.png" \
  -F prompt="Replace the sky with a sunset"

More from Google

All Google image models

Prices synced November 3, 2026.