Flux 2 Klein Base 9b Text To Image API Documentation

Flux 2 Klein Base 9b Text To Image API Documentation

Playground

FLUX.2 [klein] Base 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

WaveSpeed AI FLUX.2 Klein Base 9B Text-to-Image generates images from natural-language prompts with a simple interface for prompt input, output size selection, and optional seed control. It is suitable for concept art, creative ideation, marketing visuals, and other prompt-driven image generation workflows.

Why Choose This?

• Prompt-based image generation Turn natural-language descriptions into generated images with minimal setup.

• Simple control surface Only a few core inputs are required, making the workflow easy to use and integrate.

• Flexible image size Use the size parameter to control the output dimensions.

• Seed support for reproducibility Use seed to get more consistent generations across repeated runs.

• Production-ready API Suitable for image generation tools, prototyping pipelines, and creative applications.

Parameters

How to Use

1. Write your prompt — describe the subject, style, lighting, composition, and mood you want.
2. Choose size (optional) — set the output dimensions if you want something other than the default.
3. Set a seed (optional) — use a fixed seed for more reproducible results, or -1 for random generation.
4. Submit — run the model and download the generated image.

Example Prompt

A cinematic futuristic city street at night, neon reflections on wet pavement, atmospheric fog, ultra-detailed, dramatic lighting

Pricing

Just $0.015 per image.

Billing Rules

• Each generated image costs $0.015
• size and seed do not affect pricing
• Pricing is fixed per generated image

Best Use Cases

• Concept art — Explore visual ideas and creative directions quickly.
• Marketing creatives — Generate visuals for campaigns, ads, and presentations.
• Social media content — Produce prompt-driven images for posts and promotional content.
• Creative prototyping — Test visual ideas before moving into heavier production workflows.
• General image generation — Create still images from short or detailed prompts.

Pro Tips

• Be specific in your prompt about subject, environment, style, and lighting.
• Start with the default size for quick generation, then adjust if needed.
• Use the same seed when you want more consistent variations of a concept.
• Use -1 when you want a fresh random result each time.
• Short, focused prompts often produce more controllable results than overly broad descriptions.

Notes

• prompt is required.
• size defaults to 1024*1024.
• seed defaults to -1, which means random generation.
• Pricing is fixed at $0.015 per image.

Related Models

• FLUX.2 Klein Base 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 Base 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-base-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