Seedream 3.0

ByteDanceImages

ByteDance Seedream 3.0: affordable text-to-image with tidy in-image text.

Our price
$0.022
per image
Official
$0.030
25% vs official

First request

from openai import OpenAI

client = OpenAI(
    base_url="https://api.altrouter.ai/v1",
    api_key="ar-...",
)

img = client.images.generate(
    model="seedream-3",
    prompt="a red fox in the snow",
)
print(img.data[0].url)

The interface is OpenAI-compatible: in existing code only the base_url, the key and the model id change — nothing else.

Seedream 3.0 against its price neighbours

Seedream 3.0 and its closest neighbours by price: prices and parameters from the AltRouter AI catalog
ModelPriceUnitDiscount
Recraft Crisp UpscaleRecraft$0.0034image−15%Open
Recraft Remove BackgroundRecraft$0.0085image−15%Open
Seedream 3.0this pageByteDance$0.022image−25%
Imagen 4 FastGoogle$0.023imageOpen
Qwen Image 3.0Alibaba$0.028image−8%Open

Prices and parameters come from the same catalog as the price above; this is not a benchmark, it is comparable billing terms.

Limits

Pricing is flat — $0.022 per image, regardless of prompt length. Allowed image_size values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9.

There is no subscription: every successful request is billed at the price above, and a failed one is not billed at all. That price is already 25% below the vendor's official one — the official price is shown struck through next to it so it can be checked. No ByteDance account of your own is needed, and no VPN: requests go to api.altrouter.ai and we make the upstream call.

Rate limiting is shared across models and counted per key: 600 requests per minute by default, and a 429 with retry-after: 60 above it. An individual key can get its own limit and a spending cap per day, week, month or lifetime in the dashboard.

Full limits and credits

When to pick Seedream 3.0, and when a neighbour

The cheaper neighbour is Recraft Remove Background: $0.0085 per image against $0.022 for Seedream 3.0. On the same volume the bill comes out 2.6× smaller. It is the sensible pick where the task is repetitive and high-volume — labelling, classification, short templated answers — the kind of work where quality is bounded by the prompt rather than the model.

The dearer neighbour is Imagen 4 Fast: $0.023 per image, or 1× the price. On catalog parameters it offers the same capabilities and the same order of context, so the premium is only justified if Seedream 3.0 falls short on your own task.

Guessing is more expensive than checking: the table above is prices and parameters, not a benchmark, and it cannot tell you which model does better on your own prompt. Switching costs one line — the model id in the request changes, the base_url and the key stay — so running both on your own data takes minutes.

API

OpenAI-compatible image generation endpoint. The result is re-hosted on our CDN and returned as a URL.

POST/v1/images/generations
Body parameters
modelstringrequired"seedream-3"
The model id.
promptstringrequired
The text description of the image.
image_sizeenumsquare_hd · square · portrait_4_3 · portrait_16_9 · landscape_4_3 · landscape_16_9default square_hd
Image size / orientation preset.
guidance_scalenumber1–10default 2.5
How strictly to follow the prompt.
seednumber0–2147483647
Seed for reproducibility.
Response
createdinteger
Unix creation time (seconds).
dataarray
Images. Each: url (our CDN), b64_json, revised_prompt.
Example
cURLPythonJavaScriptJSON
curl https://api.altrouter.ai/v1/images/generations \
  -H "Authorization: Bearer ar-..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream-3",
  "prompt": "a red fox in the snow",
  "image_size": "square_hd"
}'
Errors
400Invalid request.
401Missing or invalid API key.
402Insufficient credits, or the key’s spending cap is exhausted.
404Model not found.
429Rate limit exceeded.

More from ByteDance