Flux Schnell API Documentation

Flux Schnell API Documentation

Playground

FLUX.1 [schnell] is a 12B rectified flow transformer for high-quality text-to-image generation via API. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

wavespeed-ai/flux-schnell is an ultra-fast text-to-image model designed for high-throughput generation and rapid iteration. It’s ideal when you want to explore ideas quickly, batch-generate variations, or power real-time creative workflows with consistent, production-friendly latency.

What it’s good at

• Fast text-to-image generation for rapid prompt iteration
• High-throughput batches (great for grids, A/B testing, and variations)
• Concepting & ideation (style exploration, composition discovery)
• Lightweight production use where speed matters more than maximum fidelity

Inputs

• prompt (required): your text description
• image (optional): reference image (if enabled in your deployment)
• mask_image (optional): mask for inpainting / local edits (if enabled)
• strength (optional): how strongly the model follows the reference/mask edit intent
• size: output resolution (width/height)
• num_images: number of images to generate
• seed: random seed (-1 for random)
• output_format: output format (e.g., jpeg)
• enable_base64_output (API only): return base64 instead of a URL
• enable_sync_mode (API only): wait for generation to finish before returning

Recommended settings

• Quick iterations: keep prompts short and specific, generate multiple candidates (num_images > 1)
• More control: lock the seed, then tweak one prompt element at a time
• Editing/inpainting: start with strength ~0.6–0.85, then adjust based on how much change you want

Use cases

• Marketing creative drafts: generate dozens of on-brand concept options fast
• Game & animation concept art: rapid character/prop/environment exploration
• Design exploration: packaging, posters, thumbnails, UI mood boards
• Prompt prototyping: build “prompt recipes” before switching to higher-fidelity models
• Batch generation pipelines: large-scale variation sweeps for selection and ranking

Pricing

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",
  "strength": 0.8,
  "size": "1024*1024",
  "num_images": 1,
  "seed": -1,
  "output_format": "jpeg"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-schnell" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters