Kwaivgi Kling Image V4.0 Text To Image API Documentation

Kwaivgi Kling Image V4.0 Text To Image API Documentation

Playground

Try it on WaveSpeedAI!

Kling Image 4.0 Text-to-Image generates photorealistic images from text prompts with strong typography and detailed composition, making it suitable for product visuals, posters, marketing assets, branded content, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Kling Image 4.0 Text-to-Image generates images from text prompts at 2K, 4K, or 8K. Describe a scene, illustration, poster, or product concept, then choose the aspect ratio and number of images.


Why Choose This?

  • Text-guided generation — Describe subjects, composition, lighting, and visual style.
  • Resolution options — Choose from 2K, 4K, and 8K output tiers.
  • Flexible framing — Select one of eight aspect ratios.
  • Batch generation — Request 1–9 independent images per call.

Parameters

ParameterRequiredDescription
promptYesDescribe the image, including any text you want to appear.
aspect_ratioNo1:1, 3:2, 2:3, 3:4, 4:3, 9:16, 16:9, or 21:9. Default: 1:1.
resolutionNoOutput resolution tier: 2k, 4k, or 8k. Default: 2k.
num_imagesNoNumber of independent output images, from 1 to 9. Default: 1.
output_formatNoOutput format: png, jpeg, or webp. Default: png.

How to Use

  1. Write a prompt — Describe the subject, setting, composition, and style.
  2. Choose framing and resolution — Select an aspect ratio and the 2k, 4k, or 8k tier.
  3. Set the image count — Choose how many independent images to generate.
  4. Select a format and submit — Choose png, jpeg, or webp, then review the results.

Pricing

Pricing is based on the selected resolution and num_images.

ResolutionPrice per output image
2K$0.063
4K$0.094
8K$0.157

Total price = num_images × the selected resolution rate.

Example Costs

ConfigurationPrice
1 image at 2K$0.063
4 images at 4K$0.376
9 images at 8K$1.413

Best Use Cases

  • Concept development — Explore scenes, characters, and visual directions.
  • Poster layouts — Draft promotional artwork with text instructions.
  • Product concepts — Visualize products in different settings.

Pro Tips

  • Specify the main subject, camera angle, lighting, and background.
  • Put requested wording in quotation marks and describe its placement.
  • Use multiple outputs to compare different interpretations of the same prompt.

Notes

  • prompt is required.
  • Pixel dimensions depend on the selected resolution and aspect ratio.
  • Review generated text and fine details before use.

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": "2k",
  "num_images": 1,
  "output_format": "png"
}
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/kwaivgi/kling-image-v4.0/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

Retry temporary errors only while polling, never the submit request. Errors, retries and timeouts

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-Text prompt for image generation. Text you quote in the prompt (titles, labels, signs) is rendered in the image.
aspect_ratiostringNo1:11:1, 3:2, 2:3, 3:4, 4:3, 9:16, 16:9, 21:9The aspect ratio of the generated image. Defaults to 1:1.
resolutionstringNo2k2k, 4k, 8kOutput resolution. 2k, 4k or native 8k.
num_imagesintegerNo11 ~ 9Number of independent images to generate.
output_formatstringNopngpng, jpeg, webpOutput image format.

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

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.statusstringTask status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses.
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.statusstringStatus: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.