ByteDance

Seedream 5.0

seedream-5.0-flash

ByteDance's production-grade image generation model, supporting web retrieval and multi-step logical reasoning, 4K output, and example-based editing, suitable for product images and infographic creation

seedream-5.0-flash seedream-5.0-lite/image-to-image seedream-5.0-lite/text-to-image seedream-5.0-pro/image-to-image seedream-5.0-pro/text-to-image

Try seedream-5.0-flash

Input

Showcases

View all showcases

Output

image

Fill in the parameters and run — results show up here.

Pricing

seedream-5.0-flash per image

Unit Price	$0.025

Positioning Overview

Seedream 5.0 Flash is the fast image generation model in the ByteDance Seedream 5.0 series, supporting both text-to-image and image-to-image paths. It accepts up to 10 reference images, allows you to specify 1K, 1.5K, 2K, or custom width and height sizes, and supports transparent backgrounds and JPEG/PNG output format selection. It is suitable for developers who need to produce product images, marketing assets, and series visuals in batches. It can be integrated through the unified HiAPI.ai interface, using reference images and prompts to complete generation and modification.

Core Highlights

Image-to-image with multi-reference image input — You can pass a single URL, Base64, or an array of up to 10 images, using a set of reference images to constrain characters, style, and composition.
Flexible output size control — Supports 1K, 1.5K, 2K presets or custom width and height, with aspect ratios covering 1:16 to 16:1, suitable for banner and vertical assets.
Optional transparent background output — During single-image editing, you can specify a transparent background and output PNG, making it easy to overlay assets directly onto design drafts or pages.
Prompt optimization toggle — Built-in standard prompt optimization mode improves generation stability without changing the invocation logic.

Capability Description

Dual paths of text-to-image and image-to-image: Generate an image from a prompt alone, or combine reference images to specify modification locations and content. One interface covers needs from creating new assets to modifying existing images.

Multi-image reference and fusion: Image-to-image supports up to 10 reference images, and you can identify the role of each image in the prompt for style consistency and multi-element composition.

Controllable output size and format: You can specify 1K to 2K or custom width and height, and output JPEG or PNG; transparent background editing is automatically constrained to single-image input and PNG format.

Generation watermark toggle: The watermark parameter is disabled by default and can be explicitly enabled to add an AI-generated watermark, making it easy to switch according to the compliance requirements of publishing channels.

Use Cases

E-commerce developers producing product images in batches — Use actual product photos as reference images and combine prompts to generate versions with different backgrounds and compositions, producing assets that can be used directly on detail pages and in advertising.
Series visual extension for marketing teams — Pass in a key visual reference image and describe variant requirements to batch-produce posters, banners, and other assets with consistent size and style.
Scenario-based image invocation in design tools — Call the interface with text or image input within a product to provide users with instant image generation and modification capabilities.

Limitations and Selection Advice

As a Flash model, it is aimed at conventional image generation and reference-image editing, with a maximum output size of 2K and no higher-resolution output option. Transparent backgrounds are limited to single-image editing and must output PNG, so this capability cannot be used simultaneously in batch multi-image reference scenarios. If you need higher resolution, complex infographics, or pixel-level fine editing, you should evaluate more capable versions in the same series; for scenarios with extremely high generation quality requirements and acceptable longer wait times, separate selection is also recommended.

What's new

View changelog →

New model seedream-5.0-pro/image-to-image Now Available Nov 3, 2026
New model New model launched: seedream-5.0-pro/text-to-image Nov 3, 2026
New model seedream-5.0-lite/image-to-image model now available Nov 3, 2026

Create a generation task

POST https://api.hiapi.ai/v1/tasks

Headers

AuthorizationstringRequired

Account API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key

Content-TypestringOptional

The request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.

Idempotency-KeystringOptional

Idempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.

Idempotency key

On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.

Body

modelstringRequired

Current fixed value: seedream-5.0-flash

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for seedream-5.0-flash and route default — see the parameter table below.

sizestringOptionalDefault: "2K"pattern ^(1K|1\.5K|2K|[1-9][0-9]{0,3}x[1-9][0-9]{0,3})$

Controls the dimensions of the generated image. Accepts 1K, 1.5K, 2K, or a custom size in the form "width x height"; custom sizes must have a total pixel count between 921600 and 4624220, and an aspect ratio between 1:16 and 16:1. Defaults to 2K.

imageanyOptionalminLength 1minItems 1maxItems 10pattern ^(https?://|data:image/)

Reference image input. Accepts a single URL, a Base64 image, or an array of up to 10 images, used to guide generation or editing. Required when background is transparent.

promptstringRequiredminLength 1maxLength 5000

Describes the image content you want to generate; when used with reference images, you can specify which areas and content should be modified.

watermarkbooleanOptionalDefault: false

Controls whether to add an AI-generated watermark to the output image; pass true to enable. Disabled by default (false).

backgroundstringOptionalDefault: "opaque"

Controls the output background type. Defaults to opaque; when set to transparent, it applies only to editing a single image with an alpha channel, and the output format must be PNG or unspecified.

Options:opaquetransparent

output_formatstringOptional

Specifies the file format of the output image; when omitted it is usually JPEG, or PNG for transparent backgrounds. When background is transparent, only png is supported.

Options:jpegpng

optimize_prompt_optionsobjectOptional

Prompt optimization settings group; controls options related to prompt optimization.

modestringOptionalDefault: "standard"

Controls the prompt optimization mode, using the standard optimization mode. Defaults to standard.

Options:standard

callbackobjectOptional

Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.

Callbacks (Webhook)

Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.

urlstringRequired

Required when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.

whenstringOptionalDefault: "final"

Only final is supported today — notified on both success and fail.

Options:final

storagestringOptionalDefault: "temp"

Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.

Options:temppersistent

Request examples

# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer $HIAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream-5.0-flash",
  "input": {
    "size": "2K",
    "prompt": "…",
    "watermark": false,
    "background": "opaque"
  }
}'

const res = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "seedream-5.0-flash",
    input: {
      "size": "2K",
      "prompt": "…",
      "watermark": false,
      "background": "opaque"
    }
  }),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } }

import os, requests

res = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
    json={
        "model": "seedream-5.0-flash",
        "input": {
          "size": "2K",
          "prompt": "…",
          "watermark": False,
          "background": "opaque"
        }
    },
)
print(res.json())  # { code, message, data: { taskId } }

200 OK

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
  }
}

400 Bad Request

{
  "code": 400,
  "message": "invalid request",
  "data": null,
  "error_code": "INVALID_REQUEST"
}

Get task detail

GET https://api.hiapi.ai/v1/tasks/:id

Response fields

taskIdstringRequired

Task ID, always prefixed with tk-hiapi-.

modelstringRequired

Resolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.

routestringOptional

Present only when the task was submitted with an explicit route parameter; echoes the submitted value.

statusstringRequired

Task status.

Status values

queued Queued, not started yet. handling Being processed. archiving Processing finished, artifacts being prepared. success Terminal: completed, artifacts available (output returned). fail Terminal: failed (error returned). After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.

creatednumberRequired

Task creation time (Unix seconds).

completednumberRequired

Unix seconds when the task reached a terminal state; fixed to 0 while not terminal.

outputarrayOptional

Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).

Array [ object ]

Array items

urlstringRequired

Artifact URL, directly downloadable.

typestringRequired

Current possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.

expireAtnumberRequired

Unix seconds until which the artifact remains accessible; download or transfer before it expires.

errorobjectOptional

Present only when status == fail.

codestringRequired

Business error code.

messagestringRequired

Error description.

Response examples

Success

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
    "model": "happyhorse-1-0",
    "status": "success",
    "created": 1777282033,
    "completed": 1777282099,
    "output": [
      {
        "url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
        "type": "video",
        "expireAt": 1777886899
      }
    ]
  }
}

Processing (non-terminal)

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "archiving",
    "created": 1777282033,
    "completed": 0
  }
}

Failed

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "fail",
    "created": 1777282033,
    "completed": 1777282099,
    "error": {
      "code": "TASK_FAILED",
      "message": "task failed"
    }
  }
}