API Free WeekHundreds of APIs are free to call this week.Browse free APIs

Seedream 5.0 Flash Editing

bytedance/seedream/5.0/flash/edit

Seedream 5.0 Flash Editing edits and fuses up to 10 reference images from a text instruction at one flat price per image, with fast 15–20 second turnaround.

Base price
$0.02USD / run
Execution
async
Model type
image
Input fields
4

Try the model

Playground

Open playground
Input

PNG, JPEG, WebP, or GIF · 20 MiB maximum each · up to 10

Reference images to edit or fuse (1–10). Refer to them in the prompt as image 1, image 2, ...
The text prompt to generate an image from.
The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 1:1, 3:4, 2:3, 9:16.
The format of the generated image. Allowed values: jpeg, png.
OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price
$0.02 / run

Context & modalities

Input
Schema-defined
Output
image

Capabilities

Chat
Not supported
Vision
Not supported
Reasoning
Not supported
Structured output
Not supported
Function calling
Not supported
Audio input
Not supported

Access

Provider
Bytedance
Model ID
bytedance/seedream/5.0/flash/edit
Execution
async
API
Unified Run API
Endpoint
/v1/run

API README

Seedream 5.0 Flash Editing

Seedream 5.0 Flash Editing is the speed-and-volume tier of ByteDance Seedream 5.0. It edits a supplied image or fuses up to 10 reference images according to a written instruction, keeping the identity and composition that should stay stable. Typical generation time is about 15–20 seconds, which makes it a practical default for iteration, campaign variants, and high-volume pipelines; use Seedream 5.0 Pro when maximum fidelity matters more than speed.

Highlights

  • Fast turnaround. Around 15–20 seconds per image, several times faster than Seedream 5.0 Pro.
  • One flat price. Every image costs the same regardless of aspect ratio, and reference images are free.
  • Instruction-led composition. The prompt coordinates subject, setting, style, layout, and requested text.
  • Multi-image fusion. Combine up to 10 reference images in one request.

Pricing

ConfigurationBilling unitPrice
Any aspect ratioPer image$0.018

Reference images are not billed. Price follows the BytePlus ModelArk list price.

When to Use

✅ Good fit❌ Consider alternatives
Fast edits or fusion of existing visualsMaximum detail and complex instructions (Seedream 5.0 Pro)
Campaign variants, social assets, concept explorationBatch sequences of related images (Seedream 5.0 Lite)

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API
Unified Run API endpoint
https://api.sandbase.ai/v1/run
Model ID
bytedance/seedream/5.0/flash/edit
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "bytedance/seedream/5.0/flash/edit",
  "images": [
    "https://p9-arcosite.byteimg.com/tos-cn-i-goo7wpa0wc/77024d8e03f24862b066bfc385301120~tplv-goo7wpa0wc-image.image",
    "https://p9-arcosite.byteimg.com/tos-cn-i-goo7wpa0wc/2cbc5cf5a68d44899fc52f177fb9cf51~tplv-goo7wpa0wc-image.image"
  ],
  "prompt": "Generate 3 images of a girl and a cow plushie happily riding a roller coaster in an amusement park, depicting morning, noon, and night.",
  "output_format": "png"
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All language models
ModelContextInput / 1MOutput / 1MReleased
Bytedance———Sep 15, 2026
Bytedance———Sep 15, 2026
Bytedance———Jul 8, 2026
Bytedance———Jul 8, 2026
Bytedance———Apr 28, 2026
Bytedance———Mar 23, 2026