Seedream 4.5 Text to Image API

POST /v1/tasks

All models are called through the Unified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name	seedream-4.5/text-to-image
Type	Image generation (text-to-image)
Endpoint	POST /v1/tasks
Pricing	See HiAPI Pricing

Seedream 4.5 text-to-image: ByteDance's community-favorite quality tier with solid photorealism and in-image text rendering, 8 ratios, 2K/4K at one flat per-image price.

Production guidance

For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
Use callback.when=final. Both success and fail are terminal states, so your service should deduplicate by taskId.

Best suited for

Photoreal & commercial assets

The community-favorite quality tier: product shots, ads and photoreal scenes with solid detail.

promptresolution

In-image text rendering

Accurate English and Chinese text on signs and posters — brand and marketing ready.

prompt

8 ratios + 4K

From 21:9 banners to 9:16 portrait, with 2K/4K at the same price.

aspect_ratioresolution

Per-image billing

One flat rate per image regardless of resolution.

resolution

Request parameters

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

# Create an async task — returns taskId immediately (generation runs async)
# Replace YOUR_API_KEY with your account API key
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream-4.5/text-to-image",
  "input": {
    "prompt": "A majestic snow leopard resting on a rocky ledge at dawn, breath visible in the cold air, golden alpine light, cinematic composition, ultra-detailed, high dynamic range",
    "aspect_ratio": "16:9",
    "resolution": "4K"
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "seedream-4.5/text-to-image",
  "input": {
    "prompt": "A majestic snow leopard resting on a rocky ledge at dawn, breath visible in the cold air, golden alpine light, cinematic composition, ultra-detailed, high dynamic range",
    "aspect_ratio": "16:9",
    "resolution": "4K"
  }
}
''')

# Create an async task — returns taskId immediately (generation runs async)
resp = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json=payload,
)
print(resp.json())  # Returns { code, message, data: { taskId } }

// Create an async task — returns taskId immediately (generation runs async)
// Replace YOUR_API_KEY with your account API key
const resp = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "seedream-4.5/text-to-image",
  "input": {
    "prompt": "A majestic snow leopard resting on a rocky ledge at dawn, breath visible in the cold air, golden alpine light, cinematic composition, ultra-detailed, high dynamic range",
    "aspect_ratio": "16:9",
    "resolution": "4K"
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Fixed value seedream-4.5/text-to-image.

example seedream-4.5/text-to-image

input object required

Business parameters. Put Seedream 4.5 Text to Image-specific configuration here.

prompt string required

A text description of the image you want to generate. Max 3000 characters.

aspect_ratio enum required

Width-height ratio of the generated image.

default 1:1 enum: 1:14:33:416:99:162:33:221:9

resolution enum required

Output image resolution. 2K for standard quality, 4K for ultra HD.

default 2K enum: 2K4K

callback object optional

Optional callback configuration. When set, HiAPI notifies your service when the task reaches a terminal state.

url string required

Required when callback is set; HTTPS URL that receives terminal task notifications.

example https://your-domain.com/hiapi/callback

when enum optional

Callback trigger timing. Use final.

default final enum: final

Example requests

Snow leopard at dawn (4K)

Tested photoreal wildlife shot, 16:9 ultra HD.

Request body

{
  "model": "seedream-4.5/text-to-image",
  "input": {
    "prompt": "A majestic snow leopard resting on a rocky ledge at dawn, breath visible in the cold air, golden alpine light, cinematic composition, ultra-detailed, high dynamic range",
    "aspect_ratio": "16:9",
    "resolution": "4K"
  }
}

Ramen shop sign (Chinese text)

Tested Chinese calligraphy sign rendering, 3:4 portrait.

Request body

{
  "model": "seedream-4.5/text-to-image",
  "input": {
    "prompt": "A cozy ramen shop storefront at night with a glowing hand-painted signboard that reads 一碗入魂 in bold calligraphy, steam rising, rain-slicked street reflections, warm lantern light",
    "aspect_ratio": "3:4",
    "resolution": "2K"
  }
}

Getting the result

The response returns a taskId immediately without waiting for generation to finish.
In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
When status=success, download the generated image from output[].url.
When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.

FAQ

Seedream 4.5 vs 5.0-lite?

4.5 is the quality tier with stronger photorealism and text rendering; 5.0-lite is the budget/speed tier.

Do 2K and 4K cost the same?

Yes — per-image billing is resolution-independent, so 4K is usually the right choice.

Can it edit reference images?

Use the sibling seedream-4.5/image-to-image for edits and composites with up to 14 references.