Bytedance Seedream V5.0 Flash API Documentation

Bytedance Seedream V5.0 Flash API Documentation

Playground

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.

Features

Seedream V5.0 Flash is the fast, lower-cost tier of Seedream 5.0. It shares Seedream V5.0 Pro’s capabilities — information-dense layouts, precise composition, and native multilingual text — and generates images faster at a lower price, for latency- and cost-sensitive image workflows.

Why Choose This?

• Pro capabilities, Flash speed
  Same capability set as Seedream V5.0 Pro, tuned for faster generation.

• One price for every resolution
  1k, 1.5k, and 2k all cost the same, so choose the tier your output needs.

• Flexible aspect ratios
  Supports square, portrait, landscape, tall, wide, and cinematic aspect ratios.

• Multilingual text rendering
  Render headlines, labels, and signage directly in the image in many languages.

• Standard output formats
  Generate images in jpeg or png format.

Parameters

How to Use

1. Write your prompt — Describe the subject, scene, style, lighting, composition, and visual details.
2. Choose aspect ratio — Select the layout that matches your target format.
3. Choose resolution — 1k, 1.5k, or 2k; the price is the same.
4. Choose output format — Select jpeg or png.
5. Submit — Generate the final image.

Pricing

A flat $0.027 per image at every resolution.

Best Use Cases

• High-volume generation — Social posts, ad variants, thumbnails, and e-commerce imagery at scale.
• Marketing visuals with text — Posters, banners, and promotional images with rendered copy.
• Fast creative iteration — Explore compositions and copy quickly before a final render.
• Localized assets — Produce the same creative with text in different languages.
• Layout-specific assets — Generate square, portrait, landscape, tall, wide, or cinematic images.

Pro Tips

• Put the exact text you want rendered in quotes and say where it goes.
• Write in-image text in its target language.
• Use detailed prompts with subject, composition, lighting, style, mood, and background details.
• Since every resolution costs the same, pick 2k whenever the image will be cropped or printed.
• Use 9:16 for vertical mobile content and 16:9 for widescreen layouts.
• For hero assets that need the highest quality, re-run the final prompt on Seedream V5.0 Pro.

Related Models

• Seedream V5.0 Flash Edit — Edit images with text instructions.
• Seedream V5.0 Pro — Higher-quality Seedream 5.0 image generation.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "aspect_ratio": "1:1",
  "resolution": "1k",
  "output_format": "jpeg"
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedream-v5.0-flash" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters