---
title: "GPT Image 2"
method: POST
path: "/api/v1/gpt-image-2"
tags: ["ImageAPI"]
---

# GPT Image 2

`POST /api/v1/gpt-image-2`

**Pricing (tokens/image, USD at $0.02/token)** — aligned to OpenAI gpt-image-2 cost (official x1.3):

| quality | 1k | 2k | 4k |
|---|---|---|---|
| low | 0.39 ($0.008) | 0.78 ($0.016) | 1.17 ($0.023) |
| medium | 3.45 ($0.069) | 6.9 ($0.138) | 10.35 ($0.207) |
| high | 13.72 ($0.274) | 27.44 ($0.549) | 41.16 ($0.823) |

Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated image.

## Headers

- `Authorization` string

## Request body

- object
  - `prompt` string, required — Text prompt describing the image.
  - `ratio` 'auto' | '1:1' | '16:9' | '9:16' | '4:3' | '3:4' | '2:3' | '3:2' | '4:5' | '5:4' | '21:9' — Aspect ratio.
  - `image_size` '1k' | '2k' | '4k' — Output resolution. See pricing table above.
  - `quality` 'low' | 'medium' | 'high' — Image quality: low / medium / high. See pricing table above.
  - `image_list` object[] — Optional reference images, [{"url": "https://..."}], max 4.
    - `url` string, uri
  - `custom_callback_url` string, uri — Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt.

## Response `200`

- object
  - `code` integer, required
  - `msg` string, required
  - `data` object, required
    - `img_uuid` string, required

## Other responses

- `401`

---

[API](https://skmtc.net/goenhance/apis/goenhance-api.md) · [All operations](https://skmtc.net/goenhance/apis/goenhance-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/goenhance/goenhance-api/versions/0f636e1b6caf/schema)