Seedream 5.0 Lite API

What it does

Seedream 5.0 Lite makes images from a prompt and up to 14 reference images: one image, or a group of up to 15 related images in one task, such as a storyboard, a set of product views or a series in one style. The prompt goes in input.prompt, the reference images in input.image, and sequential_image_generation turns on the group. The fields you send choose the mode:

Every example below is a complete body for POST /v1/generations. Send the same body to POST /v1/estimates first: it is free, creates no task, holds no Credits, and refuses an invalid body with the same 422 as a create. The https://media.vizoapi.com/... files are public samples, so the examples run as they are; replace them with your own files or uploaded ast_... asset IDs.

Modes

Text to image

Send only prompt. Pick the size with size: 2k, 3k, or an exact WIDTHxHEIGHT (see [Output](#output)). For 4K, send the pixel size, such as 3840x2160; the word 4k is refused.

{
  "model": "seedream-5-0-lite",
  "input": {
    "prompt": "A paper boat on a still pond at dawn, mist on the water, soft natural light, watercolor illustration",
    "size": "2k",
    "output_format": "png"
  }
}

Reference images and editing

Put 1 to 14 images in image, in the order you want to name them. With one image, the prompt can edit it: change an object, the background, the light or the style, and say what must stay. With several, combine them, and name each by its order in the prompt ("image 1", "image 2"). A 15th image is refused (rule too_many_items). Reference images are included in the price.

{
  "model": "seedream-5-0-lite",
  "input": {
    "prompt": "Turn image 1 into a night scene: a starry sky and a thin crescent moon above the monolith; keep the composition unchanged",
    "image": [
      "https://media.vizoapi.com/samples/seedance-2-5/odyssey-v1/keyframes/monolith.jpg"
    ],
    "size": "2k"
  }
}

{
  "model": "seedream-5-0-lite",
  "input": {
    "prompt": "The ring-shaped space station from image 2 floats in the sky above the monolith from image 1, golden hour, wide shot",
    "image": [
      "https://media.vizoapi.com/samples/seedance-2-5/odyssey-v1/keyframes/monolith.jpg",
      "https://media.vizoapi.com/samples/seedance-2-5/odyssey-v1/keyframes/station.jpg"
    ],
    "size": "2560x1440"
  }
}

Group of images

Set sequential_image_generation to auto and sequential_image_generation_options.max_images to the number of images you want, 1 to 15. The model makes a set of related images that share characters, style and setting; describe the set in the prompt ("4 storyboard panels: …"). All images in a group share size and output_format.

• auto without sequential_image_generation_options is refused (rule max_images_required).
• sequential_image_generation_options without auto is refused (rule group_options_without_auto).
• Reference images plus max_images must be at most 15 (rule too_many_images): with 3 reference images, max_images is at most 12.

max_images is an upper limit: the model may return fewer images. The hold covers max_images, and the charge counts the images delivered.

{
  "model": "seedream-5-0-lite",
  "input": {
    "prompt": "Four storyboard panels of a paper boat's journey: launched by a child's hand at a pond, drifting through reeds, caught in rain, arriving at a lantern-lit dock at night. Same boat, same watercolor style in every panel.",
    "sequential_image_generation": "auto",
    "sequential_image_generation_options": { "max_images": 4 },
    "size": "2k"
  }
}

{
  "model": "seedream-5-0-lite",
  "input": {
    "prompt": "Three posters for the same film, using the space station from image 1: a teaser in black space, a close-up of its docking ring, a wide shot above an amber planet. Same color palette, clean title space at the top.",
    "image": [
      "https://media.vizoapi.com/samples/seedance-2-5/odyssey-v1/keyframes/station.jpg"
    ],
    "sequential_image_generation": "auto",
    "sequential_image_generation_options": { "max_images": 3 },
    "size": "2304x3072",
    "output_format": "png"
  }
}

Prompt optimization

Any mode can set "optimize_prompt": true to have the prompt rewritten before generation. optimize_prompt_options tunes it: thinking is auto, enabled or disabled, and mode is only standard. Sending optimize_prompt_options without "optimize_prompt": true is refused (rule optimize_options_without_optimize). The price does not change.

{
  "model": "seedream-5-0-lite",
  "input": {
    "prompt": "cozy reading corner, rainy evening",
    "optimize_prompt": true,
    "optimize_prompt_options": { "thinking": "auto", "mode": "standard" },
    "size": "2k"
  }
}

Input limits

Plain http, private or local addresses, URLs with a user name or #fragment, and Base64 data are refused with 422 (rule bad_format). The model fetches a linked image itself, possibly some time after acceptance, so keep it reachable until the task closes; if it cannot, the task fails with generation_failed. See Model inputs and media.

Output

A succeeded task lists its images in result.outputs, in the order the model made them: one image, or 1 to max_images for a group. Each is a PNG or JPEG as output_format asks; take each asset_id and get a download URL with download an asset. Outputs are kept for 7 days. See Get results.

How it is billed

The model has one tier, standard, at 7 Credits per output image. Reference images, size, output_format, seed, optimize_prompt and watermark do not change the price.

The hold is the price × the images you ask for: 1, or max_images for a group.

A succeeded task is charged for the images delivered, never more than you asked for: if a group of 4 returns 3 images, price.charged is 21.000 and the rest of the hold is released. A failed, canceled or unresolved task is not charged. Send the body to POST /v1/estimates to see the exact hold and its basis (outputs, input_images). See Billing.

Errors and behaviors

Moderation is always on; no field turns it off. Each task has a 24-hour deadline from acceptance. A task still unfinished then closes as unresolved, releases its hold and is not charged; if its result arrives later, it is added at no charge and late_result_available becomes true. See Errors and Get results.

Prompting tips

• Describe the picture, not the process: subject, setting, composition, light and style. Full sentences work better than a list of keywords.
• For a group, say how many images and what each one shows ("Panel 1: …, Panel 2: …"), and what stays the same across them: the character, the outfit, the palette, the style. Set max_images to the number you describe.
• To edit, say exactly what changes and what stays: "replace the sky with a storm; keep the people, their pose and the framing unchanged".
• With several references, name each by its order and say what to take from it: "the jacket from image 2 on the person in image 1".
• Put text you want in the image in quotes, and say where it goes: a title "NORTH STAR" at the top, in bold white letters.
• Pick size for the framing: a tall 2304x3072 for posters and phone screens, a wide 2560x1440 or 3840x2160 for banners.

Pricing

Each output image is billed at the tier’s price.

Rules

• optimize_prompt_options is allowed only with optimize_prompt set to true.
• sequential_image_generation_options is required when sequential_image_generation is auto and allowed only then; reference images plus max_images are at most 15.

Input fields

Send these fields in input. A field the table does not list is refused with HTTP 422 invalid_input.

Example

A complete create request, the 202 answer and the task once it has succeeded.

Request

curl https://api.vizoapi.com/v1/generations \
  -H "Authorization: Bearer $VIZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream-5-0-lite",
  "input": {
    "prompt": "A paper boat on a pond at dawn, soft watercolor"
  },
  "metadata": {
    "client_reference": "my-unique-reference-1"
  }
}'

import os, requests

# Send once: do not retry this request automatically.
task = requests.post(
    "https://api.vizoapi.com/v1/generations",
    headers={"Authorization": f"Bearer {os.environ['VIZO_API_KEY']}"},
    json={
      "model": "seedream-5-0-lite",
      "input": {
        "prompt": "A paper boat on a pond at dawn, soft watercolor"
      },
      "metadata": {
        "client_reference": "my-unique-reference-1"
      }
    },
    timeout=60,
).json()
print(task["id"], task["status"])

// Send once: do not retry this request automatically.
const res = await fetch("https://api.vizoapi.com/v1/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.VIZO_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "seedream-5-0-lite",
    "input": {
      "prompt": "A paper boat on a pond at dawn, soft watercolor"
    },
    "metadata": {
      "client_reference": "my-unique-reference-1"
    }
  }),
});
const task = await res.json();
console.log(task.id, task.status);

Response

{
  "id": "gen_01JD8Z5QW3XR",
  "model": "seedream-5-0-lite",
  "source": "api",
  "created_at": "2026-11-08T09:00:00Z",
  "customer_resolution_deadline": "2026-11-09T09:00:00Z",
  "late_result_available": false,
  "metadata": {
    "client_reference": "my-unique-reference-1"
  },
  "status": "processing",
  "execution_status": "processing",
  "delivery_status": "pending",
  "billing_status": "pending",
  "version": 1,
  "price": {
    "unit": "credit",
    "estimated": "7.000",
    "reserved": "0.000",
    "charged": "0.000",
    "refunded": "0.000"
  },
  "allowed_actions": [],
  "closed_at": null,
  "error": null,
  "result": null
}

{
  "id": "gen_01JD8Z5QW3XR",
  "model": "seedream-5-0-lite",
  "source": "api",
  "created_at": "2026-11-08T09:00:00Z",
  "customer_resolution_deadline": "2026-11-09T09:00:00Z",
  "late_result_available": false,
  "metadata": {
    "client_reference": "my-unique-reference-1"
  },
  "status": "succeeded",
  "execution_status": "succeeded",
  "delivery_status": "ready",
  "billing_status": "settled",
  "version": 4,
  "price": {
    "unit": "credit",
    "estimated": "7.000",
    "reserved": "0.000",
    "charged": "7.000",
    "refunded": "0.000"
  },
  "allowed_actions": [],
  "closed_at": "2026-11-08T09:01:31Z",
  "error": null,
  "result": {
    "asset_id": "ast_01JD8Z9M2C4V",
    "outputs": [
      {
        "index": 0,
        "asset_id": "ast_01JD8Z9M2C4V",
        "content_type": "image/jpeg"
      }
    ]
  }
}