Real-time web search
Its headline feature is web-connected retrieval, so it can ground generations in current events, trending topics, recently released products, and live information like today's weather.
Image by ByteDance
Seedream 5.0 API
ByteDance's flagship Seedream 5.0 image model (early 2026), a unified multimodal model that pairs deep reasoning with real-time web search to ground images in current, real-world information.
Integrate Seedream 5.0 with a single API call — one key, one unified endpoint, and shared billing across every model on Apiframe.
model: "seedream-5" What's special about Seedream 5.0
Flagship-grade visual reasoning
It uses multi-step, chain-of-thought thinking to read the intent behind an instruction like a designer would, producing more physically plausible results with fewer hallucinations than the Lite variant.
Deep world knowledge
It draws on broad knowledge across technology and the humanities, which makes it strong for information-dense work like infographics, educational diagrams, and technical illustrations.
Best-in-class instruction following
It follows long, multi-part prompts reliably and sets the family high-water mark for subject consistency and image-text alignment.
Multi-image input and batch sets
It accepts up to 14 reference images for fusion and composition, and generates coherent image sets for campaigns and series.
High-resolution, commercially tuned output
It targets the family’s top quality tier for e-commerce, marketing, and cinematic looks, while keeping per-image cost competitive.
Made with Seedream 5.0
A few outputs generated through the Seedream 5.0 API on Apiframe.
Sample coming soon
A cinematic portrait of an astronaut in a neon-lit alley, 85mm, shallow depth of field
Sample coming soon
Cozy isometric coffee shop, warm morning light, highly detailed 3D render
Sample coming soon
A majestic snow leopard on a misty mountain ridge at golden hour
Overview
- Endpoint
- POST /v2/images/generate
- Model ID
- seedream-5
- Params key
- seedreamParams
- Modality
- Image
- Provider
- ByteDance
- Avg. completion
- ~15s
Capabilities
Aspect ratios1:1, 3:4, 4:3, 9:16, 16:9
Image inputSupported
Avg. time~15s
Quick start
Send a single POST /v2/images/generate request with your API key to
generate with Seedream 5.0. The call returns a jobId you can poll or
receive via webhook.
curl -X POST https://api.apiframe.ai/v2/images/generate \
-H "X-API-Key: afk_your_api_key_here" \
-H "Content-Type: application/json" \
-d '{
"prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
"model": "seedream-5",
"seedreamParams": {
"image_input": "https://example.com/input.jpg",
"output_format": "jpg",
"guidance_scale": 3,
"use_pre_llm": false
}
}'import requests
response = requests.post(
"https://api.apiframe.ai/v2/images/generate",
headers={
"X-API-Key": "afk_your_api_key_here",
"Content-Type": "application/json",
},
json={
"prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
"model": "seedream-5",
"seedreamParams": {
"image_input": "https://example.com/input.jpg",
"output_format": "jpg",
"guidance_scale": 3,
"use_pre_llm": False
}
},
)
print(response.json()) # { "jobId": "...", "status": "QUEUED" }const response = await fetch("https://api.apiframe.ai/v2/images/generate", {
method: "POST",
headers: {
"X-API-Key": "afk_your_api_key_here",
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
"model": "seedream-5",
"seedreamParams": {
"image_input": "https://example.com/input.jpg",
"output_format": "jpg",
"guidance_scale": 3,
"use_pre_llm": false
}
}),
});
const { jobId } = await response.json();
console.log(jobId);Response & job lifecycle
Generation is asynchronous. A successful submission returns 202 Accepted with a jobId. Poll GET /v2/jobs/{id} (or supply a webhook_url) until the status is COMPLETED; the result field then holds the output URL(s).
1. Submission response (202)
{
"jobId": "b2c3d4e5-f6a7-8901-bcde-f23456789012",
"status": "QUEUED"
}2. Poll for the result
curl https://api.apiframe.ai/v2/jobs/JOB_ID \
-H "X-API-Key: afk_your_api_key_here"import requests, time
while True:
job = requests.get(
"https://api.apiframe.ai/v2/jobs/JOB_ID",
headers={"X-API-Key": "afk_your_api_key_here"},
).json()
if job["status"] in ("COMPLETED", "FAILED"):
break
time.sleep(2)
print(job["result"])let job;
do {
await new Promise((r) => setTimeout(r, 2000));
job = await fetch("https://api.apiframe.ai/v2/jobs/JOB_ID", {
headers: { "X-API-Key": "afk_your_api_key_here" },
}).then((r) => r.json());
} while (job.status !== "COMPLETED" && job.status !== "FAILED");
console.log(job.result);Input schema
Request parameters accepted by the Seedream 5.0 endpoint. Model-specific options are nested under the params object shown below.
| Parameter | Type | Required | Default | Allowed / range | Description |
|---|---|---|---|---|---|
| prompt | string | required | — | — | Text description of what to generate. |
| model | string | required | "seedream-5" | "seedream-5" | The model identifier for this endpoint. |
| seedreamParams.image_input | string (URL) | optional | — | — | Reference image (URL) |
| seedreamParams.output_format | string | optional | "jpg" | "jpg", "png" | Output format |
| seedreamParams.guidance_scale | number | optional | 3 | min 1, max 10, step 0.5 | Guidance |
| seedreamParams.use_pre_llm | boolean | optional | false | — | Pre-process the prompt with an LLM. |
| seedreamParams.enhance_prompt | boolean | optional | false | — | Enhance prompt |
| seedreamParams.seed | number | optional | — | step 1 | Reuse a number to reproduce the same result. |
Frequently Asked Questions
Common questions about the Seedream 5.0 API.
What is Seedream 5.0?
The flagship member of ByteDance's Seedream 5.0 family, a unified multimodal image model with deep reasoning and built-in real-time web search.
What is web search in it?
It pulls real-time information from the web at generation time, so images can reflect current trends, events, products, and data rather than only training knowledge.
How is it different from Seedream 5 Lite?
It is the full-size flagship: more compute, stronger reasoning, and higher overall quality, where Lite trades some of that for speed and lower cost.
How is it different from Seedream 4.5?
It adds real-time search and deep reasoning, with stronger instruction following, consistency, and world knowledge, and a higher overall Elo score.
How many reference images can it use?
Up to 14 in a single generation, for fusion and composition.
Where can you access it?
Through Apiframe, as well as ByteDance's Dreamina and CapCut apps and major hosting partners.
Still have questions?
Start building with the Seedream 5.0 API
Get your API key and integrate Seedream 5.0 in minutes — Pay-as-you-go.
Free credits to start
One API for every model
Webhooks, SDKs & idempotency
No provider account required
Questions? Join our Discord or contact sales.