Generate Images via Flatkey Using gpt-image-2 and More

Generate images from text prompts at up to 50% off official pricing using Flatkey’s /v1/images/generations endpoint. It is fully compatible with the OpenAI images API, so you can use gpt-image-2 and other supported models with the OpenAI SDK or a direct REST call.

Supported image models

Model	Official price	After-bonus price
`gpt-image-2`	$6.65 / 1M tokens	~$3.99 / 1M tokens
`gemini-3-pro-image`	$2.00 / 1M tokens	~$1.20 / 1M tokens
`gemini-2.5-flash-image`	$0.30 / 1M tokens	~$0.18 / 1M tokens

See the Model Directory for the full image model list.

Quick start with the OpenAI SDK

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["FLATKEY_API_KEY"],
    base_url="https://router.flatkey.ai/v1",
)

response = client.images.generate(
    model="gpt-image-2",
    prompt="A serene mountain lake at sunset, photorealistic",
    size="1024x1024",
    n=1,
)

print(response.data[0].url)

import OpenAI from "openai";

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

const response = await client.images.generate({
  model: "gpt-image-2",
  prompt: "A serene mountain lake at sunset, photorealistic",
  size: "1024x1024",
  n: 1,
});

console.log(response.data[0].url);

With curl

curl https://router.flatkey.ai/v1/images/generations \
  -H "Authorization: Bearer $FLATKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A futuristic cityscape at night, neon lights, wide angle",
    "size": "1024x1024",
    "n": 1
  }'

Parameters

model

string

required

The image model to use. E.g. gpt-image-2, gemini-3-pro-image.

prompt

string

required

A text description of the image to generate. More detailed prompts produce better results.

integer

Number of images to generate (default: 1). Maximum depends on the model.

size

string

Image dimensions. Common values: "256x256", "512x512", "1024x1024", "1792x1024", "1024x1792". Support varies by model.

response_format

string

"url" (default) returns a temporary URL. "b64_json" returns base64-encoded image data.

Response format

{
  "created": 1710000000,
  "data": [
    {
      "url": "https://...",
      "revised_prompt": "A serene mountain lake at sunset..."
    }
  ]
}

URLs returned from image generation are temporary and expire after a short period. Download and store images you want to keep.

Writing effective prompts

Be specific about style: photorealistic, oil painting, watercolor, 3D render
Include lighting details: golden hour, studio lighting, dramatic shadows
Specify composition: close-up, wide angle, bird’s eye view, portrait orientation
Add quality modifiers: highly detailed, 4K, professional photography

​Supported image models

​Quick start with the OpenAI SDK

​With curl

​Parameters

​Response format

​Writing effective prompts

Supported image models

Quick start with the OpenAI SDK

With curl

Parameters

Response format

Writing effective prompts