Skip to content
HiAPI Docs
HiAPI
Playground Get API Key
English
English 中文

Seedream 5.0 Pro 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-5.0-pro/text-to-image
Type Image generation (text-to-image)
Endpoint POST /v1/tasks
Pricing See HiAPI Pricing

HiAPI flagship text-to-image model with upgraded fidelity and in-image text rendering: basic/high quality tiers and 8 aspect ratios for posters, e-commerce and photorealistic work.

Production guidance

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

Text-heavy layouts

Posters, signage and menus are a strength, with sharp multilingual text rendering — spell out every word you want in the prompt (verified with brush-calligraphy Chinese and neon English signs).

prompt
Photorealistic portraits and commercial finish

Flagship quality tier with solid skin texture, lighting depth and material detail for portraits, product shots and cinematic scenes.

prompt
Tiered cost control

basic outputs 1K images at $0.05/image; high outputs 2K images at $0.10/image. Billing is tiered by quality, so iterate with basic to save.

quality
Flexible aspect ratios

Eight aspect ratios cover square, landscape, portrait and ultrawide canvases.

aspect_ratio

Request parameters

model string required

Fixed value seedream-5.0-pro/text-to-image.

example seedream-5.0-pro/text-to-image
input object required

Business parameters. Put Seedream 5.0 Pro Text to Image-specific configuration here.

prompt string required

Text prompt for image generation, 4-5000 characters. Keep under ~600 English words for best results.

aspect_ratio enum required

Width-height ratio of the generated image.

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

Output quality tier. basic outputs a 1K image at $0.05/image; high outputs a 2K image at $0.10/image.

default basic enum: basichigh
output_format enum optional

Output image format.

default png enum: pngjpeg
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

Chinese tea house poster (brush calligraphy)

3:4 / 1K — exercises Chinese calligraphy glyphs and poster layout.

Request body
{
  "model": "seedream-5.0-pro/text-to-image",
  "input": {
    "prompt": "An elegant vintage Chinese tea house poster, hand-painted lettering reads 山水茶社 in refined brush calligraphy, minimal composition with mountain-and-water ink wash background, muted celadon and vermilion palette, cinematic composition, ultra-detailed",
    "aspect_ratio": "3:4",
    "quality": "basic"
  }
}
Cyberpunk night market (English signage)

16:9 / 1K — rainy neon scene with crisp English storefront lettering.

Request body
{
  "model": "seedream-5.0-pro/text-to-image",
  "input": {
    "prompt": "A neon-lit night market street in a rainy cyberpunk city, a glowing storefront sign reads \"SEEDREAM 5 PRO\" in crisp lettering, cinematic composition, dramatic directional lighting, rich cohesive color grade, ultra-detailed, premium commercial finish, subtle film grain, shallow depth of field, high dynamic range",
    "aspect_ratio": "16:9",
    "quality": "basic"
  }
}
Calligraphy master portrait (photorealism)

3:4 / 1K — golden window light portrait exercising skin texture and shallow depth of field.

Request body
{
  "model": "seedream-5.0-pro/text-to-image",
  "input": {
    "prompt": "Close-up portrait of an elderly Chinese calligraphy master mid-brushstroke, ink-stained fingers, warm golden window light carving deep facial texture, shallow depth of field, cinematic composition, ultra-detailed, premium commercial finish",
    "aspect_ratio": "3:4",
    "quality": "basic"
  }
}

Getting the result

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

FAQ

What is the difference between basic and high? Do they cost the same?

basic outputs a 1K image at $0.05/image; high outputs a 2K image at $0.10/image. Billing is tiered by quality, so iterate with basic and switch to high for final delivery. View pricing

Can it render text accurately inside images?

Multilingual text rendering is a strength — brush calligraphy and neon signage came out glyph-accurate in our tests. Spell out every word verbatim in the prompt and zoom-check critical copy.

Seedream 5.0 Pro or Lite — which should I pick?

Pro is the flagship quality tier with stronger detail, finish and portraits for final delivery; Lite is cheaper with built-in web knowledge, better for high-volume iteration and infographics.

How do I get the generated image?

The request returns a taskId immediately; once the task reaches a terminal state, download from output[].url. In production, pass callback.url at the top level to receive terminal notifications instead of polling.

Next steps