---
title: "Seedream 4.5"
method: POST
path: "/api/v1/seedream-4-5"
tags: ["ImageAPI"]
---

# Seedream 4.5

`POST /api/v1/seedream-4-5`

Seedream 4.5 text-to-image and image-to-image. Provide a `prompt`; pass `image_list` with one or more reference images to run image-to-image.

Resolution is determined by `ratio` (aspect) + `image_size` (tier); all tiers are billed the same.

**Pricing:** 1.85 tokens per image (= $0.037).

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' | '2:3' | '3:2' | '3:4' | '4:3' | '4:5' | '5:4' | '9:16' | '16:9' | '21:9' | '9:21' — Aspect ratio. Combined with `image_size` to determine the output resolution.
  - `image_size` '2K' | '4K' — Resolution tier. Combined with `ratio` to determine the output resolution (e.g. ratio `1:1` + `2K` = 2048x2048, + `4K` = 4096x4096).
  - `image_list` object[] — Optional reference images for image-to-image, e.g. [{"url": "https://..."}]. Max 14 images, each <=10MB.
    - `url` string, uri, required
  - `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/revisions/0f636e1b6caf/schema)