Image generation, built into your product.

Overview

The Ideogram API gives you programmatic access to the same models that power the Ideogram app. You send a prompt and any reference images, and the response carries hosted URLs for the results.

It can support production pipelines, whether you're generating millions of images a day or just want to automate repetitive design work.

Teams use it to build custom visual workflows in their products, power user-facing creation tools, and produce production-ready assets at volume.

Image URLs are ephemeral. They are available for a limited time after generation, so download anything you intend to keep and store it in your own system.

Capabilities

Each capability is one call away. Open any of them for examples and the request that produces them.

Generate → Turn a prompt into a finished image, with text that comes out sharp. Transparent backgrounds → Generate assets with native transparency, ready to drop into a design. Edit with a prompt → Change an image by describing the change in plain language. Remix → Reimagine an image, steering how close it stays with image_weight. Reframe → Extend an image to a new aspect ratio without losing the focal point. Remove background → Return a clean cutout with native transparency in one call. Layerized text → Pull editable text layers out of a finished design. Custom models → Train on your own images and generate consistent, on-brand output. Upscale → Raise resolution for delivery without losing detail.

Quickstart

Send a prompt to the Ideogram 4.0 generate endpoint and read the image URL from the first item in data.

import requests

response = requests.post(
    "https://api.ideogram.ai/v1/ideogram-v4/generate",
    headers={"Api-Key": "<your-api-key>"},
    json={
        "text_prompt": "A poster for a summer design conference"
    },
)

image = response.json()["data"][0]
print(image["url"])

curl -X POST https://api.ideogram.ai/v1/ideogram-v4/generate \
  -H "Api-Key: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "text_prompt": "A poster for a summer design conference"
  }'

const res = await fetch(
  "https://api.ideogram.ai/v1/ideogram-v4/generate",
  {
    method: "POST",
    headers: {
      "Api-Key": "<your-api-key>",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      text_prompt: "A poster for a summer design conference"
    }),
  },
);

const { data } = await res.json();
console.log(data[0].url);

Models and rendering speed

Pick a model family per endpoint, then trade latency against fidelity with rendering_speed.

Links

The full reference, request and response schemas, and an interactive playground live in the developer docs.