Image Generation

Portkey’s AI gateway supports image generation capabilities that many foundational model providers offer.

The most common use case is that of text-to-image where the user sends a prompt which the image model processes and returns an image.

The guide for vision models is available here.

Text-to-Image Usage

Portkey supports the OpenAI signature to make text-to-image requests.

NodeJS

import Portkey from 'portkey-ai';

// Initialize the Portkey client
const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
    provider:"@PROVIDER"   
});

async function main() {
  const image = await portkey.images.generate({
    model: "dall-e-3",
    prompt: "Lucy in the sky with diamonds"
  });

  console.log(image.data);
}

main();

Python

from portkey_ai import Portkey
from IPython.display import display, Image

# Initialize the Portkey client
portkey = Portkey(
    api_key="PORTKEY_API_KEY",  # Replace with your Portkey API key
    provider="@PROVIDER"   
)

image = portkey.images.generate(
  model="dall-e-3",
  prompt="Lucy in the sky with diamonds"
)

# Display the image
display(Image(url=image.data[0].url))

OpenAI NodeJS

import OpenAI from 'openai'; // We're using the v4 SDK
import { PORTKEY_GATEWAY_URL, createHeaders } from 'portkey-ai'

const openai = new OpenAI({
  apiKey: 'OPENAI_API_KEY', // defaults to process.env["OPENAI_API_KEY"],
  baseURL: PORTKEY_GATEWAY_URL,
  defaultHeaders: createHeaders({
    provider: "openai",
    apiKey: "PORTKEY_API_KEY" // defaults to process.env["PORTKEY_API_KEY"]
  })
});

async function main() {
  const image = await openai.images.generate({
    model: "dall-e-3",
    prompt: "Lucy in the sky with diamonds"
  });

  console.log(image.data);
}

main();

OpenAI Python

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders
from IPython.display import display, Image

client = OpenAI(
    api_key='OPENAI_API_KEY',
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        provider="openai",
        api_key="PORTKEY_API_KEY"
    )
)

image = client.images.generate(
  model="dall-e-3",
  prompt="Lucy in the sky with diamonds",
  n=1,
  size="1024x1024"
)

# Display the image
display(Image(url=image.data[0].url))

cURL

curl "https://api.portkey.ai/v1/images/generations" \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-provider: $OPENAI_PROVIDER" \
  -d '{
    "model": "dall-e-3",
    "prompt": "Lucy in the sky with diamonds"
  }'

Image Editing

Portkey supports the OpenAI signature to make image edit requests using multipart form data.

from portkey_ai import Portkey

portkey = Portkey(api_key="PORTKEY_API_KEY", provider="openai")
with open("image.png", "rb") as image_file:
  image = portkey.images.edit(
    model="gpt-image-2",
    prompt="Add snow",
    image=[("image.png", image_file.read(), "image/png")],
    size="1024x1024",
  )

Image edit models currently do not support provider-prefixed model slugs in the request body. Pass the provider in headers and keep model as the raw provider model name.

API Reference

• Create Image
• Create Image Edit

OpenAI gpt-image-1 Parameters

For OpenAI’s gpt-image-1 model, additional parameters are supported:

Parameter	Type	Description
moderation	string	Content moderation level for generated images
output_format	string	Output format for the generated image
output_compression	number	Compression level (0-100) for the output image
background	string	Background style for the generated image
partial_images	number	Number of partial images to return (0-3)
stream	boolean	Whether to stream partial image results

On completion, the request will get logged in the logs UI where the image can be viewed.

(Note that providers may remove the hosted image after a period of time, so some logs might only contain the url)

Cookbook

Here’s a detailed cookbook on image generation using Portkey which demonstrates the use of multiple providers and routing between them through Configs.