Images

Generate images from text prompts using DALL-E through the OpenAI-compatible API with BYOK support.

Availability. Image generation is enabled per organization and is off by default. POST /v1/images/generations answers 503 with Image generation unavailable for this organization until it is turned on for your account. Ask support to enable it before building against this endpoint.

Generate images from text prompts using the image generation API. Requests are proxied to OpenAI's DALL-E API with automatic BYOK key resolution.

POST /v1/images/generations
Auth: Authorization: Bearer <token>
Drop-in compatible with the OpenAI Images API.

Quick start

curl -sS https://api.xantly.com/v1/images/generations \
  -H "Authorization: Bearer $XANTLY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dall-e-3",
    "prompt": "A futuristic city skyline at sunset, digital art style",
    "n": 1,
    "size": "1024x1024"
  }'

Request body

Field	Type	Required	Description
`prompt`	`string`	Yes	Text description of the image to generate.
`model`	`string`	No	`"dall-e-3"` (default) or `"dall-e-2"`.
`n`	`integer`	No	Number of images to generate (`1`-`10`). DALL-E 3 only supports `n=1`.
`size`	`string`	No	Image size: `"1024x1024"` (default), `"1024x1792"`, `"1792x1024"` (DALL-E 3), or `"256x256"`, `"512x512"` (DALL-E 2).
`quality`	`string`	No	`"standard"` (default) or `"hd"`. DALL-E 3 only.
`style`	`string`	No	`"vivid"` (default) or `"natural"`. DALL-E 3 only.
`response_format`	`string`	No	`"url"` (default) or `"b64_json"`.
`user`	`string`	No	End-user identifier.

Response body

{
  "created": 1741400000,
  "data": [
    {
      "url": "https://oaidalleapiprodscus.blob.core.windows.net/...",
      "revised_prompt": "A futuristic city skyline at sunset..."
    }
  ]
}

Field	Type	Description
`created`	`integer`	Unix epoch timestamp.
`data`	`array`	Generated images.
`data[].url`	`string`	URL of the generated image (when `response_format` is `"url"`). URLs expire after 1 hour.
`data[].b64_json`	`string`	Base64-encoded image data (when `response_format` is `"b64_json"`).
`data[].revised_prompt`	`string`	The prompt after DALL-E 3 revision (may differ from input).

Code examples

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["XANTLY_API_KEY"],
    base_url="https://api.xantly.com/v1",
)

response = client.images.generate(
    model="dall-e-3",
    prompt="A cat wearing a space helmet, oil painting",
    size="1024x1024",
    quality="standard",
    n=1,
)
print(response.data[0].url)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.XANTLY_API_KEY,
  baseURL: "https://api.xantly.com/v1",
});

const response = await client.images.generate({
  model: "dall-e-3",
  prompt: "A cat wearing a space helmet, oil painting",
  size: "1024x1024",
  quality: "standard",
  n: 1,
});
console.log(response.data[0].url);

BYOK support

The images endpoint automatically resolves your organization's BYOK OpenAI key. If no BYOK key is configured, the platform key is used as a fallback.

Errors

HTTP	`error.type`	Typical trigger
`400`	`invalid_request_error`	Missing prompt, invalid size, unsupported parameters.
`401`	`authentication_error`	Missing or invalid Bearer token.
`500`	`provider_error`	No OpenAI API key configured, or upstream error.

Next steps

Chat Completions, Main inference endpoint
Audio, Speech-to-text and text-to-speech
Models, List available models