Skip to main content
ModelRunner
bytedance avatar

Seedream 5.0 Pro API

bytedance/seedream-v5-pro

Generate and edit high-resolution images from a text prompt and up to 10 reference images — the premium, precision-editing tier of Seedream 5.0.

edit
0.09
OpenAPI

Model Input

Input

Text prompt describing the image to generate, or the edit to apply to the reference image(s).

Optional reference image(s) for editing and reference-based generation. Provide up to 10 images; omit entirely for pure text-to-image.

Output image dimensions as WxH pixels. Values at or below ~2.36 megapixels (e.g. 1024x1024, 1376x768) bill at the lower price tier; higher-resolution values (e.g. 2048x2048, 2752x1536) bill at the premium tier.

You need to be logged in to run this model and view results.
Log in

Model Output

Output

Generated image output
Generated in 154.711 seconds
Logs (1 lines)

Model Example Requests

Examples

Example output 1Example output 2Example output 3

Seedream 5.0 Pro API

Seedream 5.0 Pro is a image-to-image AI model by bytedance. On ModelRunner it runs through a REST API or via MCP from any AI assistant, at $0.09 per image.

POST https://queue.modelrunner.run/bytedance/seedream-v5-pro

cURL

# Submit a request to the queue. Input fields go at the top level of the
# body. The optional reserved "metadata" object holds your own flat string
# tags — stored on the request, never sent to the model; filter later with
# GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>.
curl -X POST https://queue.modelrunner.run/bytedance/seedream-v5-pro \
  -H "Authorization: Key $MRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "size": "2048x2048",
    "prompt": "A bustling futuristic night market on a rain-slicked street: glowing multilingual neon signage, steam rising from foo…",
    "metadata": {
      "project": "my-project"
    }
  }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }

# Poll status_url until "COMPLETED", then fetch the result
curl "https://queue.modelrunner.run/bytedance/seedream-v5-pro/requests/$REQUEST_ID/status" \
  -H "Authorization: Key $MRUN_API_KEY"
curl "https://queue.modelrunner.run/bytedance/seedream-v5-pro/requests/$REQUEST_ID" \
  -H "Authorization: Key $MRUN_API_KEY"

JavaScript

import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("bytedance/seedream-v5-pro", {
  input: {
    "size": "2048x2048",
    "prompt": "A bustling futuristic night market on a rain-slicked street: glowing multilingual neon signage, steam rising from foo…"
  },
});
console.log(result);

Python

import os
import requests

headers = {"Authorization": f"Key {os.environ['MRUN_API_KEY']}"}

submitted = requests.post(
    "https://queue.modelrunner.run/bytedance/seedream-v5-pro",
    headers=headers,
    json={
      "size": "2048x2048",
      "prompt": "A bustling futuristic night market on a rain-slicked street: glowing multilingual neon signage, steam rising from foo…"
    },
).json()

# Poll submitted["status_url"] until "COMPLETED", then:
result = requests.get(submitted["response_url"], headers=headers).json()

Input parameters

NameTypeRequiredDescription
promptstringyesText prompt describing the image to generate, or the edit to apply to the reference image(s).
image_urlsarraynoOptional reference image(s) for editing and reference-based generation. Provide up to 10 images; omit entirely for pure text-to-image.
sizeenumnoOutput image dimensions as WxH pixels. Values at or below ~2.36 megapixels (e.g. 1024x1024, 1376x768) bill at the lower price tier; higher-resolution values (e.g. 2048x2048, 2752x1536) bill at the premium tier. Default: "1024x1024".

Machine-readable: OpenAPI schema · llms.txt

Use Seedream 5.0 Pro from Claude & Cursor (MCP)

Point Claude Code, Claude Desktop, Cursor, or any MCP client at the ModelRunner MCP server and Seedream 5.0 Pro becomes a tool your assistant can call directly — it authorizes via OAuth (no API key in config) and runs this model with the run_model tool using the endpoint bytedance/seedream-v5-pro.

MCP client config (Claude Desktop, Cursor)

{
  "mcpServers": {
    "modelrunner": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.modelrunner.run/mcp"]
    }
  }
}

Claude Code

claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcp

Then ask your assistant, for example: “Run bytedance/seedream-v5-pro on ModelRunner to generate image”. MCP setup guide.

Model Details

Model Details

Seedream 5.0 Pro is the premium tier of the Seedream 5.0 image line, unifying text-to-image generation and reference-based image editing in a single model. Give it a prompt to create an image from scratch, or add up to 10 reference images to edit, restyle, or composite existing visuals with high fidelity and precise instruction following. It renders sharp detail, accurate in-image text, and consistent subjects across references, and outputs from roughly 1 megapixel up to ~4.2 megapixels. Larger output sizes cost more per image.

## Best for - High-fidelity text-to-image with accurate, legible in-image text (posters, logos, UI mockups) - Editing or restyling a photo from a text instruction while keeping the rest of the image unchanged - Reference-based generation: transferring style, identity, or product details from up to 10 reference images - Compositing multiple products, people, or scenes into one coherent image - Premium-quality visuals where detail and prompt accuracy matter more than speed or price

## Choose another model when - You want the fastest, cheapest generation and can trade some quality — use the Lite tier `bytedance/seedream-v5/text-to-image` - You need several images from one call — this tier returns a single image per request - You need a video rather than a still image — use an image-to-video model - You only need simple text-to-image with no reference editing — a lighter image model may be enough

## Tips - `size` sets both resolution and aspect ratio; pick a ~1MP value (e.g. `1024x1024`, `1376x768`) for the lower price tier, or a ~4.2MP value (e.g. `2048x2048`, `2752x1536`) for maximum detail at the premium tier - For editing, pass the source image(s) in `image_urls` and describe the change precisely, stating what should stay unchanged - Put any text you want rendered inside quotation marks in the prompt for the most accurate spelling - Provide clear, high-resolution reference images; you can supply up to 10

To run via the ModelRunner JavaScript client: ```js import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("bytedance/seedream-v5-pro", { input: { prompt: "a serene mountain lake at golden hour, photorealistic, sharp reflection", size: "1024x1024", }, }); ```