Seedream 5 Flash API
ByteDance Seedream 5 Flash — the fast, lower-cost tier of Seedream 5. It keeps Pro's design understanding, interactive editing, and multilingual text rendering, and returns images faster at a lower price, for latency- and cost-sensitive pipelines.
Three endpoints: bytedance/seedream-v5.0-flash for text-to-image, bytedance/seedream-v5.0-flash/edit for single-image or multi-reference editing with up to 10 reference images, and bytedance/seedream-v5.0-flash/layer-decomposition for splitting one image into a base image and transparent layers. They take the same parameters as their Seedream 5 Pro counterparts — 1K / 1.5K / 2K output and jpeg or png, plus fifteen aspect ratios for generation and editing — with one price across all three resolution tiers.

About the Seedream 5 Flash API
What Seedream 5 Flash does, how it fits in the ByteDance model lineup, and why teams reach for it.
Seedream 5 Flash is a image generation and editing model from ByteDance, available through the WaveSpeedAI REST API. ByteDance Seedream 5 Flash — the fast, lower-cost tier of Seedream 5. It keeps Pro's design understanding, interactive editing, and multilingual text rendering, and returns images faster at a lower price, for latency- and cost-sensitive pipelines.
Three endpoints: bytedance/seedream-v5.0-flash for text-to-image, bytedance/seedream-v5.0-flash/edit for single-image or multi-reference editing with up to 10 reference images, and bytedance/seedream-v5.0-flash/layer-decomposition for splitting one image into a base image and transparent layers. They take the same parameters as their Seedream 5 Pro counterparts — 1K / 1.5K / 2K output and jpeg or png, plus fifteen aspect ratios for generation and editing — with one price across all three resolution tiers.
The Seedream 5 Flash family on WaveSpeedAI ships 3 REST endpoints covering Image-To-Image, Text-To-Image workflows. Each variant carries its own pricing, parameter knobs, and example outputs — pick the one that matches your input modality and production constraints, or call several from the same API key to compose multi-step pipelines.
Run Seedream 5 Flash through the same API key, billing account, and rate-limit envelope you use for the other 1,000+ AI models on WaveSpeedAI. No separate vendor setup, no per-provider SDKs, no per-vendor rate-limit envelopes — one integration covers everything from text-to-image and text-to-video through audio synthesis, 3D generation, upscaling, and editing.
Seedream 5 Flash API capabilities and release status
The model-specific details developers search for before choosing an API: availability, expected output length, reference support, and the current live fallback.
Endpoints
3 variants
Text-to-image, edit (up to 10 reference images), and layer decomposition.
Resolution
1K / 1.5K / 2K
Three output tiers, one price across all of them.
Aspect ratios
15
1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, 21:9.
Output
JPEG / PNG
Selectable per request.
All Seedream 5 Flash API endpoints
3 Seedream 5 Flash endpoints available now on WaveSpeedAI — pick the variant that matches your workflow.

Seedream v5.0 Flash Layer Decomposition
Seedream V5.0 Flash Layer Decomposition separates a single image into a base image and transparent layers faster and at lower cost than Seedream V5.0 Pro, enabling flexible compositing, image editing, asset extraction, and layered design workflows at one price for 1K / 1.5K / 2K. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Seedream v5.0 Flash
Seedream V5.0 Flash Text to Image by ByteDance generates images from text prompts faster and at lower cost than Seedream V5.0 Pro, with aspect ratio selection, multilingual text rendering, and 1K / 1.5K / 2K output at one price. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Seedream v5.0 Flash Edit
Seedream V5.0 Flash Edit by ByteDance edits and generates images from single-image or multi-reference inputs faster and at lower cost than Seedream V5.0 Pro Edit, supporting up to 10 reference images, aspect ratio selection, and 1K / 1.5K / 2K output at one price. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
See Seedream 5 Flash in action
Real outputs generated by the Seedream 5 Flash API. Hover any video to preview, click to open the full-size viewer.
How to use the Seedream 5 Flash API
Four steps from signup to a finished generation. Full Python, Node.js, and cURL examples are in the API section below.
- 1
Get an API key
Sign up for a WaveSpeedAI account and copy your API key from the dashboard. New accounts come with free starter credits — enough to run the playground a few dozen times before billing kicks in.
- 2
Submit a prediction
POST your input as JSON to https://api.wavespeed.ai/api/v3/bytedance/seedream-v5.0-flash. The endpoint returns a prediction id immediately — generations are async so you don't hold an open connection during inference.
- 3
Poll for completion
GET https://api.wavespeed.ai/api/v3/predictions/{request_id}/result. Return outputs on completed; stop with an error on failed, cancelled, timeout, or deleted; continue polling for every other status.
- 4
Read the output URL
Once status is"completed", read the URL from data.outputs[0]. The URL points to your generated media on the WaveSpeedAI CDN — image, video, audio, or 3D file depending on the Seedream 5 Flash variant you called.
What you can build with Seedream 5 Flash
Common workflows developers and creators use the Seedream 5 Flash API for.
Pro-level capability at Flash speed
Seedream 5 Flash shares Seedream 5 Pro's capability set — information-dense layouts, interactive precision editing, and native multilingual text — and is tuned for faster generation at a lower price. Use it wherever turnaround and volume matter more than the last increment of image quality.
High-volume creative production
Social posts, ad variants, thumbnails, and e-commerce imagery where hundreds of images per campaign add up. Flash keeps text rendering and layout quality while the lower per-image cost keeps large batches affordable.
Multi-reference editing
bytedance/seedream-v5.0-flash/edit accepts single-image or multi-reference inputs (up to 10 references). Place a product into a new scene, restyle an asset, or combine character and style references in one call; the output follows the first reference image's aspect ratio unless aspect_ratio is set.
Layer decomposition for design work
bytedance/seedream-v5.0-flash/layer-decomposition splits one image into a base image and up to 16 separate layers — subject, text, background, decorations — so a flat creative can be rearranged, restyled, or reused in design tools. Request png output to keep each layer's transparency.
Interactive, position-aware edits
Like Pro, Flash understands edit instructions tied to positions — coordinates, boxes, arrows, and marks drawn on the reference image — so a change can target one region while the rest of the image stays intact.
Fast iteration before a Pro final
Explore composition and copy on Flash, then re-run the chosen prompt on Seedream 5 Pro when a hero asset needs its extra quality. The request shape is the same apart from Pro's prompt optimization option, so switching is a model-ID change.
Tips for prompting Seedream 5 Flash
Practical advice for getting better outputs from Seedream 5 Flash — drawn from the patterns that work across image models in production pipelines.
Pick resolution by delivery, not by cost
Flash costs the same at 1K, 1.5K, and 2K, so choose the tier the destination needs. 1.5K is a good default for social and web; use 2K when the image will be cropped or printed.
Put the exact text in quotes
For posters, packaging, and banners, write the literal copy in quotes and say where it goes ("title at the top", "price tag bottom right"). Flash renders multilingual text natively, so write the copy in its target language.
Describe the edit, then what to keep
For bytedance/seedream-v5.0-flash/edit, state the change first and then what must not change — "replace the background with a beach at dusk, keep the product and its lighting unchanged". Explicit preservation instructions reduce drift in the untouched regions.
Order references by importance
When sending several reference images, put the main subject first; the output follows the first image's aspect ratio unless aspect_ratio is set. Refer to images by position in the prompt ("the jacket from image 2").
Draft on Flash, finalize on Pro
Iterate prompts on Flash for speed, then re-run the winning prompt on bytedance/seedream-v5.0-pro for hero assets. Parameters carry over unchanged.
Seedream 5 Flash API pricing
Pricing is per-output. The final charge scales with the parameters you set in each variant's playground (resolution, duration, output count, references).
| Endpoint | Type | Starting price |
|---|---|---|
| bytedance/seedream-v5.0-flash/layer-decomposition | image-to-image | $0.459 |
| bytedance/seedream-v5.0-flash | text-to-image | 10% OFF$0.027$0.0243 |
| bytedance/seedream-v5.0-flash/edit | image-to-image | 10% OFF$0.027$0.0243 |
Call the Seedream 5 Flash API
Sign up for an API key at wavespeed.ai/accesskey, then submit a prediction via REST. The playground generates ready-to-paste samples for any combination of inputs.
HTTP example
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/bytedance/seedream-v5.0-flash" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"resolution": "1k",
"output_format": "jpeg"
}')
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneNode.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/bytedance/seedream-v5.0-flash";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"resolution": "1k",
"output_format": "jpeg"
}),
});
const task = body.data ?? body;
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}Python example
import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"resolution": "1k",
"output_format": "jpeg"
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/bytedance/seedream-v5.0-flash", json.dumps(payload).encode())
task = body.get("data", body)
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Seedream 5 Flash vs alternatives
When to pick Seedream 5 Flash over similar models on WaveSpeedAI.
Seedream 5 Flash vs Seedream 5 Pro
Same capability set and the same parameters apart from Pro's prompt optimization mode. Both offer text-to-image, edit, and layer decomposition. Pro delivers higher image quality; Flash generates faster at a lower price. Pick Pro for hero assets, Flash for volume and latency-sensitive work.
Seedream 5 Flash vs Seedream 5 Lite
Lite is the older cost tier with Sequential variants for multi-image identity locking and custom sizes up to 4K. Flash is built on the Seedream 5 Pro generation, so it adds Pro's design understanding, interactive editing, and multilingual text rendering.
Seedream 5 Flash vs Nano Banana 2
Nano Banana 2 ships multi-character consistency and optional web-search grounding. Seedream 5 Flash answers with position-aware interactive editing, up to 10 reference images, and native multilingual text rendering at a lower per-image cost.
Seedream 5 Flash API — Frequently asked questions
Pricing, license, integration — common questions about running Seedream 5 Flash on WaveSpeedAI.
What is the Seedream 5 Flash API?
Seedream 5 Flash is a ByteDance image generation model exposed as a REST API on WaveSpeedAI. ByteDance Seedream 5 Flash — the fast, lower-cost tier of Seedream 5. It keeps Pro's design understanding, interactive editing, and multilingual text rendering, and returns images faster at a lower price, for latency- and cost-sensitive pipelines. You can call it programmatically or try it from the playground linked above.
How do I call the Seedream 5 Flash API?
Sign up for a WaveSpeedAI account, copy your API key from /accesskey, then POST to https://api.wavespeed.ai/api/v3/bytedance/seedream-v5.0-flash with your input as JSON. The endpoint returns a prediction id. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. Production-oriented Python / Node.js / cURL examples are above.
How much does the Seedream 5 Flash API cost?
Seedream 5 Flash starts at $0.0243 per run. The exact cost scales with the parameters you set (resolution, duration, output count, references). The live cost preview next to the Generate button in the playground shows the exact price for your current input.
Which Seedream 5 Flash variants are available?
WaveSpeedAI hosts 3 live Seedream 5 Flash endpoints: bytedance/seedream-v5.0-flash/layer-decomposition, bytedance/seedream-v5.0-flash, bytedance/seedream-v5.0-flash/edit. Each variant has its own playground page and pricing.
Can I use Seedream 5 Flash outputs commercially?
Commercial usage rights follow the ByteDance model license. Most ByteDance models permit commercial output use; see each model's playground page for the specific license summary, and WaveSpeedAI's Terms of Service for platform-level conditions.
Why use Seedream 5 Flash on WaveSpeedAI instead of going direct?
One API key + one billing account across Seedream 5 Flash AND 1,000+ other AI models from other providers. No per-vendor SDK setup, no separate rate-limit envelopes, no rewrite-per-vendor integration code. Pricing is typically at parity with or below ByteDance's direct API.
About ByteDance
The team behind Seedream 5 Flash and the broader ByteDance model lineup on WaveSpeedAI.
ByteDance — the company behind TikTok, CapCut, and Doubao — runs one of the largest AI research operations in the world. Its Seed and Doubao teams ship state-of-the-art models for video generation (Seedance), image generation and editing (Seedream, Nano Banana), and avatar / lip-sync work. Models are trained on internal-scale data and shipped to production through ByteDance's consumer apps before being released as APIs.
Start building with Seedream 5 Flash on WaveSpeedAI
Free starter credits on signup. One API key across 1,000+ AI models from ByteDance and every other provider.



