Skip to main content
POST
/
v1
/
images
/
generations
cURL
curl 'https://www.llmeasy.ru/v1/images/generations' \
  -H 'Authorization: Bearer sk-***REDACTED***' \
  -H 'Content-Type: application/json' \
  --data '{
    "model": "gpt-image-2",
    "prompt": "Футуристичный постер AI-продукта на светлом фоне, стеклянная фактура, чистая композиция, премиальный технологичный стиль",
    "n": 1,
    "size": "1024x1024",
    "response_format": "b64_json",
    "output_format": "png"
  }'
{
  "created": 1710000000,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAA...(truncated)"
    }
  ]
}

Documentation Index

Fetch the complete documentation index at: https://docs.llmeasy.ru/llms.txt

Use this file to discover all available pages before exploring further.

POST /v1/images/generations The text-to-image endpoint uses an application/json request body. Submit a prompt, keep the HTTP request open, and read the generated image from data[0].b64_json in the same response.
Use https://www.llmeasy.ru/v1 as the Base URL. Pass your LLMEasy API Key through Authorization: Bearer YOUR_API_KEY.
You can enter Authorization and the request body in the Playground on the right side of the page, then send the request directly to https://www.llmeasy.ru/v1/images/generations.
Do not put API keys in frontend browser code, Git repositories, tickets, screenshots, or logs. For server-side proxy calls, store API keys only in server environment variables or a secret manager.
Send these fields explicitly in every request: 
{
  "model": "gpt-image-2",
  "n": 1,
  "response_format": "b64_json",
  "output_format": "png"
}
Generate multiple images by sending multiple independent requests. Do not rely on a single request with n > 1.
sizeRatioUse case
autoAutoAutomatic size selection
1024x10241:1Square images, avatars, covers, assets
1536x10243:2Landscape posters, banners, scenes
1024x15362:3Portrait mobile covers and posters
1536x11524:3Standard landscape images, product images, content graphics
1152x15363:4Standard portrait images, mobile covers, vertical posters
2048x20481:1High-resolution square images
2048x115216:9High-resolution landscape images
3840x216016:94K landscape images
2160x38409:164K portrait images
size represents the expected aspect ratio and size tier. The actual returned pixels may be mapped or adjusted by the server. Use the decoded image dimensions instead of forcibly cropping the output to the requested value.

​
Save the image

A successful response follows the OpenAI-compatible image response shape: 
{
  "created": 1710000000,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAA...(truncated)"
    }
  ]
}
Read data[0].b64_json and save it as base64 image content. The response may include extra fields such as revised_prompt; allow these fields in your client. Always set output_format: "png". Then save the decoded image as .png without inspecting file headers. 
import base64
import json
from pathlib import Path

response = json.loads(Path("response.json").read_text(encoding="utf-8"))
b64_json = response["data"][0]["b64_json"]

if "," in b64_json and "base64" in b64_json.split(",", 1)[0]:
    b64_json = b64_json.split(",", 1)[1]

image_bytes = base64.b64decode(b64_json)
Path("output.png").write_bytes(image_bytes)
Do not rely on output_format: "jpeg" or output_format: "webp" to directly receive JPEG or WebP files. The current endpoint may still return PNG image content. If your product needs JPEG or WebP, receive PNG first and convert it in your own code.

​
Response flow

This endpoint is synchronous. After sending POST /images/generations, keep the current HTTP request open until the server responds. When generation succeeds, the image content is returned in data[0].b64_json. The endpoint does not return a task_id, and there is no separate status query or result download endpoint.

​
Timeouts and retries

  • Set HTTP client timeouts to several minutes.
  • Retry transport errors, 408, 409, 425, 429, and 5xx.
  • Do not retry 400, 401, missing parameters, or malformed requests automatically.
  • Use exponential backoff such as 3s, 8s, and 15s.
  • If duplicate images are unacceptable, record your own request ID before retrying.

Authorizations

​
Authorization
string
header
required

Используйте API Key LLMEasy как bearer token. Не публикуйте API keys во frontend-коде, скриншотах, логах, тикетах или Git-репозиториях.

Body

application/json
​
model
enum<string>
default:gpt-image-2
required

Используйте фиксированное значение gpt-image-2.

Available options:
gpt-image-2
Example:

"gpt-image-2"

​
prompt
string
required

Prompt для генерации изображения.

Example:

"Футуристичный постер AI-продукта на светлом фоне, стеклянная фактура, чистая композиция, премиальный технологичный стиль"

​
n
integer
default:1

Рекомендуется фиксировать значение 1. Для нескольких изображений отправляйте несколько отдельных запросов.

Required range: 1 <= x <= 1
Example:

1

​
size
enum<string>
default:1024x1024

Размеры и соотношения сторон изображения. auto выбирает размер автоматически; 1024x1024 и 2048x2048 — 1:1; 1536x1024 — 3:2; 1024x1536 — 2:3; 1536x1152 — 4:3; 1152x1536 — 3:4; 2048x1152 и 3840x2160 — 16:9; 2160x3840 — 9:16. Фактический размер может быть сопоставлен или скорректирован сервером, поэтому клиенту следует ориентироваться на реальные размеры декодированного изображения.

Available options:
auto,
1024x1024,
1536x1024,
1024x1536,
1536x1152,
1152x1536,
2048x2048,
2048x1152,
3840x2160,
2160x3840
Example:

"1024x1024"

​
response_format
enum<string>
default:b64_json

Рекомендуется фиксировать b64_json, чтобы стабильно сохранять изображение.

Available options:
b64_json
Example:

"b64_json"

​
output_format
enum<string>
default:png

Рекомендуется фиксировать png. Не рассчитывайте, что jpeg или webp всегда вернутся напрямую в выбранном формате.

Available options:
png
Example:

"png"

Response

Результат генерации изображения.

OpenAI-совместимый ответ с изображением. Клиентам следует читать data[0].b64_json и учитывать возможные дополнительные поля, например revised_prompt.

​
created
integer
Example:

1710000000

​
data
object[]