Kling V4.0 Flash Reference-to-Video generates high-quality videos guided by reference images and videos, with synchronized audio and a focus on fast generation for character consistency, motion guidance, social content, marketing videos, and production workflows. Ready-to-use REST inference API.
Idle
$0.094per run·~10 / $1
Use @Image1 as the female mechanic and @Image2 as the airship captain. Preserve their exact identities, hairstyles, clothing, accessories, and proportions. Opening frame: the female mechanic stands on the left side of the brass engine, body turned three-quarters toward the machinery, one hand resting naturally on a brass valve and the other holding a small wrench near her waist. The airship captain stands slightly behind her on the right, body angled toward the engine, one hand resting on the metal railing while he watches a pressure gauge. Both characters are focused on the machinery, not looking at the camera. The engine suddenly gives a short mechanical shake. The mechanic immediately tightens the valve with one controlled movement. The engine stabilizes. The captain looks from the gauge toward her, and she gives him a brief calm nod. The camera makes one subtle sideways push around both characters while keeping the engine visible. Natural steampunk interaction, restrained body language, realistic character chemistry, detailed brass machinery, cinematic industrial lighting.
Kling V4.0 Flash Reference-to-Video generates a 720p video guided by reference images and videos, with synchronized audio. Flash is the fast, lower-cost tier of Kling 4.0: 720p clips of 3 to 20 seconds with synchronized audio, for quick iteration and volume work.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Describe the video. Refer to reference images as @Image1, @Image2, ... and to reference videos as @Video1, @Video2, ... in array order. |
| images | No | Up to 10 reference images. |
| videos | No | Up to 5 reference videos, together used for up to 20 seconds. |
| keep_original_sound | No | Keep the reference video's own sound instead of generating new audio. Requires videos. Default false. |
| duration | No | 3 to 20 seconds, default 5. |
| aspect_ratio | No | auto (default, follows the references), 16:9, 9:16, 1:1 or 21:9. |
| Inputs | Price per second of output |
|---|---|
| Reference images only | $0.094 |
| With reference videos | $0.126 |
A 5 second clip costs $0.47 with images only, $0.63 with reference videos.
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/kwaivgi/kling-v4.0-flash/reference-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Kling v4.0 Flash Reference To Video below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"keep_original_sound": false,
"duration": 5,
"aspect_ratio": "auto"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v4.0-flash/reference-to-video" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v4.0-flash/reference-to-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"keep_original_sound": false,
"duration": 5,
"aspect_ratio": "auto"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"keep_original_sound": False,
"duration": 5,
"aspect_ratio": "auto"
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/kwaivgi/kling-v4.0-flash/reference-to-video", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Kling v4.0 Flash Reference To Video is a Kuaishou model for reference-guided video generation, exposed as a REST API on WaveSpeedAI. Kling V4.0 Flash Reference-to-Video generates high-quality videos guided by reference images and videos, with synchronized audio and a focus on fast generation for character consistency, motion guidance, social content, marketing videos, and production workflows. Ready-to-use REST inference API. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/kwaivgi/kwaivgi-kling-v4.0-flash-reference-to-video.
Kling v4.0 Flash Reference To Video starts at $0.094 per run or per second. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `images`, `aspect_ratio`, `duration`, `keep_original_sound`, `videos`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/kwaivgi/kwaivgi-kling-v4.0-flash-reference-to-video.
Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.
Commercial usage rights depend on the model's license, set by its provider (Kuaishou). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.