reapi-video-1

Quick example

curl https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "reapi-video-1",
    "mode": "text_to_video",
    "prompt": "A lighthouse keeper in a wool coat stands on a wet stone pier at dawn and says, \"The fog lifts at seven.\" Locked-off shot, waves slapping the stones, no music.",
    "duration": 5,
    "resolution": "768p",
    "aspect_ratio": "16:9"
  }'

import requests

resp = requests.post(
    "https://reapi.ai/api/v1/videos/generations",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "reapi-video-1",
        "mode": "text_to_video",
        "prompt": "A lighthouse keeper in a wool coat stands on a wet stone pier at dawn and says, \"The fog lifts at seven.\" Locked-off shot, waves slapping the stones, no music.",
        "duration": 5,
        "resolution": "768p",
        "aspect_ratio": "16:9",
    },
    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: "reapi-video-1",
    mode: "text_to_video",
    prompt:
      'A lighthouse keeper in a wool coat stands on a wet stone pier at dawn and says, "The fog lifts at seven." Locked-off shot, waves slapping the stones, no music.',
    duration: 5,
    resolution: "768p",
    aspect_ratio: "16:9",
  }),
});
console.log(await r.json());

package main

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

func main() {
    body, _ := json.Marshal(map[string]any{
        "model":        "reapi-video-1",
        "mode":         "text_to_video",
        "prompt":       `A lighthouse keeper in a wool coat stands on a wet stone pier at dawn and says, "The fog lifts at seven." Locked-off shot, waves slapping the stones, no music.`,
        "duration":     5,
        "resolution":   "768p",
        "aspect_ratio": "16:9",
    })
    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))
}

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.

Request body

The schema is strict: unknown fields are rejected rather than ignored. callback_url / callback_id are not accepted — poll the task, or set a webhook on your API key.

Checked before anything is submitted or charged:

• prompt is 1–32,000 characters; duration is a whole number 5–15
• image is present in image_to_video and absent in the other modes
• reference_images, reference_videos and reference_audio carry values only in reference_to_video (an empty list or null passes in any mode)
• reference_to_video has at least one reference image or video, and at most 9 images, 3 videos, 3 audio clips and 12 references in total
• adaptive is used only in reference_to_video
• every media object is exactly { "type": "url", "url": "<public http(s) URL>" }
• each reference video's length can be measured (it is billed — see Pricing); an unreadable file is rejected with nothing charged

Modes

image_to_video treats the image as the literal first frame, so the clip opens exactly as that still looks. To place a product or a person into a scene of your own, use reference_to_video and describe the scene around it.

Referencing media in the prompt

In reference_to_video, list order becomes the label you use in the prompt. The first entry of reference_images is <Picture 1>, the second <Picture 2>; the first entry of reference_videos is <Video 1>; the first entry of reference_audio is <Audio 1>. Images, videos and audio are numbered independently. Prompt enhancement can reword the rest of the prompt but not these labels; set prompt_enhancement to disabled to keep your text exactly as written.

{
  "model": "reapi-video-1",
  "mode": "reference_to_video",
  "prompt": "A supervisor wearing the harness in <Picture 1> stands still and speaks to camera.",
  "reference_images": [{ "type": "url", "url": "https://example.com/harness.jpg" }],
  "duration": 10
}

Media inputs

Every reference, and the image_to_video first frame, is an object with a public HTTP(S) URL:

{ "type": "url", "url": "https://example.com/photo.jpg" }

The URL must be reachable without redirects.

Output

The video is MP4 (H.264) at 24 fps with 32 kHz stereo AAC audio. With an explicit aspect_ratio, the size is fixed:

adaptive follows the first reference image, or the first reference video when there are no images, scaled to the short edge of the resolution with each side rounded to a multiple of 32. image_to_video follows the first frame, including its EXIF orientation — crop the image to change the shape.

Response envelope

Submit and poll share the same shape — only status and output fill in over time.

{
  "id": "task_01a10ee0e3827079aaf4165bf54fd954",
  "model": "reapi-video-1",
  "status": "completed",
  "created_at": 1791250981,
  "output": {
    "video_urls": ["https://cdn.reapi.ai/media/tasks/.../0.mp4"]
  },
  "error": null
}

Poll GET /api/v1/tasks/{id} (see the Tasks reference) every 10–20 seconds until status is completed or failed. A network timeout while polling does not mean generation failed: keep the task id and resume checking it.

Troubleshooting

Pricing

reAPI Video 1 bills per second of video, at a rate set by the mode (text / image to video vs. reference to video) and the resolution:

credits = ceil(per_second_rate × billable_seconds × 1000)     1 credit = $0.001

Live per-second rates are on the model page — that table is generated from the current price, so it is always the authoritative number.

billable_seconds = duration                                                   (text_to_video, image_to_video)
billable_seconds = duration + ceil(Σ min(each reference video's seconds, 5))  (reference_to_video)

Each reference video adds its length up to 5 seconds; a longer clip still adds 5. Reference images and audio are free. reAPI measures every reference video server-side when the request is accepted, so the amount reserved is the amount charged. An 8.6-second reference with duration: 5 bills 10 seconds. Failed tasks are always refunded in full.

Related

• reAPI Video 1 — playground and pricing
• Errors catalog
• Authentication
• Quickstart