Image Generation — POST /v1/images/generations

The /v1/images/generations endpoint generates images from text prompts. It is compatible with the OpenAI Images API and supports models including gpt-image-2 and Gemini image generation models available through Flatkey.

Endpoint

POST https://router.flatkey.ai/v1/images/generations

Request

Headers

Header	Value
`Authorization`	`Bearer $FLATKEY_API_KEY`
`Content-Type`	`application/json`

Body parameters

model

string

required

Image model ID. Example: "gpt-image-2", "gemini-3-pro-image", "gemini-2.5-flash-image".

prompt

string

required

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

integer

Number of images to generate. Default: 1. Maximum varies by model.

size

string

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

quality

string

Image quality setting. Values: "standard" or "hd". Default: "standard". Only supported by some models.

response_format

string

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

Example requests

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 futuristic city skyline at dusk, neon lights reflecting on wet streets, cyberpunk style",
    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 futuristic city skyline at dusk, neon lights reflecting on wet streets, cyberpunk style",
  size: "1024x1024",
  n: 1,
});

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

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 serene forest clearing with morning mist and sunbeams",
    "size": "1024x1024",
    "n": 1
  }'

Response

{
  "created": 1710000000,
  "data": [
    {
      "url": "https://cdn.openai.com/...",
      "revised_prompt": "A futuristic city skyline at dusk..."
    }
  ]
}

Response fields

created

integer

Unix timestamp of when the request was fulfilled.

data

array

Array of generated image objects.

Show image object

url

string

Temporary URL to the generated image. Download it promptly — URLs expire.

b64_json

string

Base64-encoded image data (only present when response_format is "b64_json").

revised_prompt

string

The prompt actually sent to the model after any safety revision.

Image URLs are temporary and expire after a short period. Download and store images you want to keep.

​Endpoint

​Request

​Headers

​Body parameters

​Example requests

​Response

​Response fields

Endpoint

Request

Headers

Body parameters

Example requests

Response

Response fields