Flux 2 Klein 9b Text To Image API Documentation

Flux 2 Klein 9b Text To Image API Documentation

Playground

FLUX.2 [klein] 9B is a high-quality text-to-image model with 9B parameters, offering enhanced realism and crisper text generation. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

FLUX.2 Klein 9B Text-to-Image is a powerful text-to-image generation model with 9B parameters. Describe your vision in text and get high-quality images with strong prompt adherence — delivering better detail and understanding than the 4B variant at an affordable price.

Why Choose This?

• Enhanced quality 9B parameter model delivers richer detail and better prompt understanding than the 4B variant.

• Strong prompt adherence Accurately interprets detailed prompts to generate images that match your description.

• Flexible sizing Custom width and height controls for any aspect ratio.

• Prompt Enhancer Built-in tool to automatically improve your prompts for better results.

• Balanced performance More capable than 4B while remaining fast and affordable.

Parameters

How to Use

1. Write your prompt — describe the image including subject, style, lighting, and mood.
2. Set size — adjust width and height for your desired dimensions.
3. Set seed — use -1 for random, or specify a number for reproducibility.
4. Run — submit and download the generated image.

Pricing

Simple flat-rate pricing regardless of image size.

Best Use Cases

• High-Quality Generation — When 4B quality isn’t enough but full-size models are overkill.
• Production Work — Balanced quality and cost for professional content.
• Creative Projects — Detailed illustrations, concept art, and visual designs.
• Batch Generation — Affordable pricing enables large-scale image production.
• Rapid Prototyping — Fast generation for creative iteration.

Pro Tips

• Be specific in your prompts — include subject, style, lighting, colors, and atmosphere.
• Use the same seed to reproduce identical outputs or compare prompt variations.
• Start with 1024x1024 for balanced quality, adjust dimensions for specific needs.
• Need custom styles? Try FLUX.2 Klein 9B Text-to-Image LoRA.

Notes

• 9B model offers better detail than 4B at slightly higher cost.
• For best results, write detailed, descriptive prompts.

Related Models

• FLUX.2 Klein 9B Text-to-Image LoRA — With LoRA support for custom styles.
• FLUX.2 Klein 4B Text-to-Image — Lighter 4B version at lower cost.
• FLUX.2 Klein 9B Edit — Image editing model.
• FLUX.2 Pro — Flagship-quality text-to-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",
  "size": "1024*1024"
}
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/wavespeed-ai/flux-2-klein-9b/text-to-image" \
  -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