rreAPI Docs
rreAPI Docs
HomeWelcome

Image

midjourney-v8flux-2z-imageqwen-image-2midjourney-v7wan-2-7-imagegpt-image-2gpt-image-2-officialgemini-2.5-flash-image-previewgemini-3-pro-image-previewgemini-3.1-flash-image-previewdoubao-seedream-5-0-liteimagen-4-0

Audio

Mureka V9 Song APIVocal Remover APIMusic Extractor APIVoice Cleaner APIMultistem Splitter APIVoice Changer API

Video

topaz-video-upscalerkling-3-0-turbokling-3-0music-video-1-0wan-2-7-videokling-motion-controlpixverse-v6doubao-seedance-2.0doubao-seedance-2.0-officialdoubao-seedance-2.0-betahappyhorse-1.0happyhorse-1.0-officialviduq3grok-imagine-video-1.5-betagrok-imagine-1.0-videoVeo 3.1gemini-omni

Chat

claude-fable-5minimax-m3deepseek-v4gpt-5.5gpt-5.4claude-opus-4-8claude-opus-4-7claude-sonnet-4-6

Text

ai-essay-writerhumanizeai-text-detector

Tools

enhance-video-1.0
X (Twitter)

kling-3-0-turbo

Kuaishou Kling 3.0 Turbo on reAPI — fast async text-to-video and image-to-video at 720p / 1080p, billed per second on one OpenAI-compatible endpoint.

Kuaishou's Kling 3.0 Turbo on reAPI — the fast tier of Kling 3.0 for text-to-video and image-to-video (first frame), at 720p or 1080p. One async endpoint: submit returns a task_id; poll until ready. See current pricing on the model page.

Quick example

curl https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-3-0-turbo",
    "prompt": "a corgi running on the beach, cinematic, golden hour",
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "duration": 5
  }'
import requests

resp = requests.post(
    "https://reapi.ai/api/v1/videos/generations",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "kling-3-0-turbo",
        "prompt": "a corgi running on the beach, cinematic, golden hour",
        "resolution": "1080p",
        "aspect_ratio": "16:9",
        "duration": 5,
    },
    timeout=30,
)
print(resp.json())
const r = await fetch("https://reapi.ai/api/v1/videos/generations", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "kling-3-0-turbo",
    prompt: "a corgi running on the beach, cinematic, golden hour",
    resolution: "1080p",
    aspect_ratio: "16:9",
    duration: 5,
  }),
});
console.log(await r.json());
package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "io"
    "net/http"
)

func main() {
    body, _ := json.Marshal(map[string]any{
        "model":        "kling-3-0-turbo",
        "prompt":       "a corgi running on the beach, cinematic, golden hour",
        "resolution":   "1080p",
        "aspect_ratio": "16:9",
        "duration":     5,
    })
    req, _ := http.NewRequest("POST",
        "https://reapi.ai/api/v1/videos/generations", bytes.NewReader(body))
    req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
    req.Header.Set("Content-Type", "application/json")

    resp, _ := http.DefaultClient.Do(req)
    defer resp.Body.Close()
    out, _ := io.ReadAll(resp.Body)
    fmt.Println(string(out))
}

Submit response

{
  "id": "task_018f5a3a1b6e7d9f8c2b4d6e8f0a2c4e",
  "model": "kling-3-0-turbo",
  "status": "processing",
  "created_at": 1735000000
}

Poll GET /api/v1/tasks/{id} (see the Tasks reference) until status === "completed". The completed payload's output.video_urls holds the generated video URL.


Authentication

Every call needs a Bearer token. Generate keys at reapi.ai/settings/apikeys.

Authorization: Bearer YOUR_API_KEY

Endpoint

POST /api/v1/videos/generations
GET  /api/v1/tasks/{id}

Submission is async. The POST returns immediately with a task_id; the task endpoint returns the same envelope until completion. Polling does not consume credits.


Modes

There is no separate model id per modality — the modality is implicit in the request shape:

  • Text-to-video — no first_frame_image. prompt is required, and aspect_ratio applies.
  • Image-to-video — pass first_frame_image (a public HTTPS URL). The clip starts from that frame, prompt is optional, and aspect_ratio is ignored (the frame fixes the ratio).

Multi-shot direction is expressed inside the prompt (describe each shot); there is no dedicated multi-shot field.


Request body

model — string, required

Must be kling-3-0-turbo.

prompt — string

Up to 3,072 characters (recommended ≤ 2,500). Required for text-to-video; optional in image-to-video (omit it to animate purely from the first frame).

first_frame_image — string, optional

Start frame for image-to-video. Public HTTPS URL only — base64 / data: URIs are rejected at the gateway. JPG / JPEG / PNG, ≤ 50 MB, ≥ 300 px, with an aspect ratio between 1:2.5 and 2.5:1.

resolution — string, default 720p

Output clarity tier: 720p or 1080p. Billed per second at the tier's rate.

duration — integer, default 5

Total video length in seconds, range 3–15. Billed per second.

aspect_ratio — string, default 16:9

One of 16:9, 9:16, 1:1. Text-to-video only. When first_frame_image is supplied (image-to-video), this field has no effect — the output ratio is determined by the first frame. Set it only for text-to-video.

watermark — boolean, optional

Add a watermark to the output video. Omitted by default (no watermark).

Modality is auto-detected: supply first_frame_image for image-to-video, omit it for text-to-video. You never set a mode flag.


Pricing

Kling 3.0 Turbo bills per second, by resolution tier (resolution):

credits = ceil(per_second_usd × seconds × 1000)

where 1 credit = $0.001 USD and seconds is duration. The 1080p tier carries a higher per-second rate than 720p. Failed and rejected requests are not charged.

The exact per-second credit cost for each tier surfaces on the model page and through the playground estimator before submit.


Response

The poll envelope returns the video URL in output.video_urls:

{
  "id": "task_019dfd44b7fd74168541552a3260a623",
  "model": "kling-3-0-turbo",
  "status": "completed",
  "output": {
    "video_urls": [
      "https://cdn.reapi.ai/...mp4"
    ]
  }
}

Generated URLs expire — mirror them to your own storage if you need long-term retention.


Errors

Failures return the standard reAPI envelope { error: { code, message, request_id } }. Common cases:

  • Invalid input (prompt over 3072 chars, out-of-range duration, a non-HTTPS first_frame_image, an invalid resolution or aspect_ratio) → 400.
  • Insufficient credits → 402.
  • Rate limited → 429.

See the full catalog at /docs/api/errors.


Tips

  • Use cinematic language in the prompt (shot type, camera move, lighting) — Kling 3.0 Turbo reads it; there is no dedicated camera-control parameter.
  • Draft at 720p to iterate cheaply, then re-run the winner at 1080p for delivery — same call, one parameter change.
  • For image-to-video, the first frame fixes the aspect ratio, so you can skip aspect_ratio in that mode.
  • Reach for the full Kling 3.0 when you need multi-shot control, native audio, or 4K; Kling 3.0 Turbo trades those for speed and a lower per-second cost.

Related

  • Kling 3.0
  • Video generation models
  • Tasks API
  • Error codes

Table of Contents

Quick example
Submit response
Authentication
Endpoint
Modes
Request body
model — string, required
prompt — string
first_frame_image — string, optional
resolution — string, default 720p
duration — integer, default 5
aspect_ratio — string, default 16:9
watermark — boolean, optional
Pricing
Response
Errors
Tips
Related