# Add to environment; never hardcode
export WISDOM_GATE_KEY="your_api_key_here"

# Confirm it's set
echo $WISDOM_GATE_KEY

A professional product photograph of a glass perfume bottle on white marble, soft studio lighting, no text

curl -s -X POST \
  "https://wisgate.ai/v1beta/models/gemini-3.1-flash-image-preview:generateContent" \
  -H "x-goog-api-key: $WISDOM_GATE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"parts": [{"text": "A minimalist ceramic coffee mug on a light oak table, morning window light"}]}],
    "generationConfig": {"responseModalities": ["IMAGE"]}
  }' \
  | jq -r '.candidates[0].content.parts[] | select(.inlineData) | .inlineData.data' \
  | head -1 | base64 --decode > output.png

curl -s -X POST \
  "https://wisgate.ai/v1beta/models/gemini-3.1-flash-image-preview:generateContent" \
  -H "x-goog-api-key: $WISDOM_GATE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [{
        "text": "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English."
      }]
    }],
    "tools": [{"google_search": {}}],
    "generationConfig": {
      "responseModalities": ["TEXT", "IMAGE"],
      "imageConfig": {
        "aspectRatio": "1:1",
        "imageSize": "2K"
      }
    }
  }' \
  | jq -r '.candidates[0].content.parts[] | select(.inlineData) | .inlineData.data' \
  | head -1 | base64 --decode > butterfly.png

import requests, base64, os

ENDPOINT = "https://wisgate.ai/v1beta/models/gemini-3.1-flash-image-preview:generateContent"

payload = {
    "contents": [{"parts": [{"text": "A luxury skincare serum bottle on white marble, warm studio lighting"}]}],
    "generationConfig": {
        "responseModalities": ["IMAGE"],
        "imageConfig": {"aspectRatio": "3:4", "imageSize": "2K"}
    }
}

response = requests.post(
    ENDPOINT,
    headers={"x-goog-api-key": os.environ["WISDOM_GATE_KEY"], "Content-Type": "application/json"},
    json=payload
)
response.raise_for_status()

for part in response.json()["candidates"][0]["content"]["parts"]:
    if "inlineData" in part:
        with open("output.png", "wb") as f:
            f.write(base64.b64decode(part["inlineData"]["data"]))
        print("Saved: output.png")
        break

const fs = require("fs");

async function generateImage(prompt, outputPath = "output.png") {
  const response = await fetch(
    "https://wisgate.ai/v1beta/models/gemini-3.1-flash-image-preview:generateContent",
    {
      method: "POST",
      headers: {
        "x-goog-api-key": process.env.WISDOM_GATE_KEY,
        "Content-Type": "application/json",
      },
      body: JSON.stringify({
        contents: [{ parts: [{ text: prompt }] }],
        generationConfig: {
          responseModalities: ["IMAGE"],
          imageConfig: { aspectRatio: "16:9", imageSize: "2K" }
        },
      }),
    }
  );

  if (!response.ok) throw new Error(`API error ${response.status}`);

  const data = await response.json();
  const imagePart = data.candidates[0].content.parts.find(p => p.inlineData);
  if (!imagePart) throw new Error("No image in response — check responseModalities");

  fs.writeFileSync(outputPath, Buffer.from(imagePart.inlineData.data, "base64"));
  console.log(`Saved: ${outputPath}`);
}

generateImage("A SaaS dashboard UI, dark mode, data visualization, minimal design", "dashboard.png")
  .catch(console.error);

{
  "candidates": [{
    "content": {
      "parts": [
        {"text": "Here is the generated image..."},
        {"inlineData": {"mimeType": "image/png", "data": "<base64-data>"}}
      ],
      "role": "model"
    },
    "finishReason": "STOP"
  }],
  "usageMetadata": {
    "promptTokenCount": 42,
    "candidatesTokenCount": 1290,
    "totalTokenCount": 1332
  }
}

import openai, os

client = openai.OpenAI(
    api_key=os.environ["WISDOM_GATE_KEY"],
    base_url="https://wisgate.ai/v1"
)

response = client.images.generate(
    model="gemini-3.1-flash-image-preview",
    prompt="A minimalist ceramic mug on oak table, morning light",
    n=1,
    size="1024x1024"
)
print(response.data[0].url)

import OpenAI from "openai";

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

const response = await client.images.generate({
  model: "gemini-3.1-flash-image-preview",
  prompt: "A minimalist ceramic mug on oak table, morning light",
  n: 1,
  size: "1024x1024",
});
console.log(response.data[0].url);

platforms = [
    ("1:1", "square.png"),
    ("16:9", "youtube.png"),
    ("9:16", "story.png"),
    ("4:5", "instagram.png"),
]
base_prompt = "A luxury skincare advertisement, warm golden lighting, minimalist"

for ar, filename in platforms:
    # make request with imageConfig.aspectRatio = ar
    print(f"Generated {ar} → {filename}")

"tools": [{"google_search": {}}]

import requests, base64, os

ENDPOINT = "https://wisgate.ai/v1beta/models/gemini-3.1-flash-image-preview:generateContent"
HEADERS = {"x-goog-api-key": os.environ["WISDOM_GATE_KEY"], "Content-Type": "application/json"}

def call_api(contents):
    r = requests.post(ENDPOINT, headers=HEADERS, json={
        "contents": contents,
        "generationConfig": {"responseModalities": ["TEXT", "IMAGE"], "imageConfig": {"imageSize": "2K", "aspectRatio": "1:1"}}
    })
    r.raise_for_status()
    return r.json()

def extract_image(response_data):
    for part in response_data["candidates"][0]["content"]["parts"]:
        if "inlineData" in part:
            return part["inlineData"]["data"]
    return None

# Turn 1 - Initial generate
contents = [{"role": "user", "parts": [{"text": "A luxury skincare serum on white marble, warm lighting"}]}]
t1 = call_api(contents)
img_b64 = extract_image(t1)
with open("turn1.png", "wb") as f:
    f.write(base64.b64decode(img_b64))

# Turn 2 - Refine
contents += [
    {"role": "model", "parts": [{"inlineData": {"mimeType": "image/png", "data": img_b64}}]},
    {"role": "user", "parts": [{"text": "Add a eucalyptus sprig to the left. Keep everything else identical."}]}
]
t2 = call_api(contents)
img_b64 = extract_image(t2)
with open("turn2.png", "wb") as f:
    f.write(base64.b64decode(img_b64))

# Turn 3 - Lighting adjust
contents += [
    {"role": "model", "parts": [{"inlineData": {"mimeType": "image/png", "data": img_b64}}]},
    {"role": "user", "parts": [{"text": "Change to cooler clinical white light. Keep composition identical."}]}
]
t3 = call_api(contents)
img_b64 = extract_image(t3)
with open("turn3.png", "wb") as f:
    f.write(base64.b64decode(img_b64))

with open("floor_plan.jpg", "rb") as f:
    ref_b64 = base64.b64encode(f.read()).decode()

payload = {
    "contents": [{"role": "user", "parts": [
        {"text": "Transform this floor plan into a photorealistic 3D interior render. Scandinavian style, natural light."},
        {"inline_data": {"mime_type": "image/jpeg", "data": ref_b64}}
    ]}],
    "generationConfig": {
        "responseModalities": ["IMAGE"],
        "imageConfig": {"aspectRatio": "16:9", "imageSize": "4K"}
    }
}

{
  "role": "model",
  "parts": [{"inlineData": {"mimeType": "image/png", "data": "<base64>"}}]
}

curl [...] > raw.json
cat raw.json | jq '.'
cat raw.json | jq '.candidates[0].content.parts[] | select(.inlineData)'

# Nano Banana 2 — bulk generation, fast, $0.058
model = "gemini-3.1-flash-image-preview"

# Nano Banana Pro — editing, hero assets, $0.068
model = "gemini-3-pro-image-preview"