seedance-2-0-mini

Generation is asynchronous: the POST returns a task id, then poll GET /api/v1/tasks/{id} until status is completed.

Quick example

curl https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer rk_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0-mini",
    "prompt": "A kitten yawning at the camera, soft morning light",
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "duration": 5
  }'

import requests

resp = requests.post(
    "https://reapi.ai/api/v1/videos/generations",
    headers={
        "Authorization": "Bearer rk_live_xxx",
        "Content-Type": "application/json",
    },
    json={
        "model": "seedance-2.0-mini",
        "prompt": "A kitten yawning at the camera, soft morning light",
        "resolution": "720p",
        "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 rk_live_xxx",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "seedance-2.0-mini",
    prompt: "A kitten yawning at the camera, soft morning light",
    resolution: "720p",
    aspect_ratio: "16:9",
    duration: 5,
  }),
});
console.log(await r.json());

package main

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

func main() {
	body, _ := json.Marshal(map[string]any{
		"model":        "seedance-2.0-mini",
		"prompt":       "A kitten yawning at the camera, soft morning light",
		"resolution":   "720p",
		"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 rk_live_xxx")
	req.Header.Set("Content-Type", "application/json")
	resp, _ := http.DefaultClient.Do(req)
	defer resp.Body.Close()
	var out map[string]any
	json.NewDecoder(resp.Body).Decode(&out)
	fmt.Println(out)
}

Endpoint

POST /api/v1/videos/generations
Authorization: Bearer rk_live_xxx
Content-Type: application/json

Submitting returns a task id; poll GET /api/v1/tasks/{id} for the result. Polling does not consume credits.

Variants

Two variants. Pick via model:

doubao-seedance-2.0-eco-mini is the economy tier. It adds 1080p, which the standard Mini does not offer at all, and starts at 720p rather than 480p. It bills on its own per-second rates — see the model page for the current numbers.

Parameters

Exactly 12 input fields, for seedance-2.0-mini. The mode is implicit — which media fields you set decides text-to-video, image-to-video, or reference-driven generation.

All media inputs (first_frame_url, last_frame_url, reference_image_urls, reference_video_urls, reference_audio_urls) must be public HTTP(S) URLs — base64 / data: URIs are rejected.

Reference files are also inspected server-side before a task is created and must be in a format the model accepts: images jpeg / png / webp / bmp / tiff / gif / heic / heif; videos an mp4 or mov container with H.264 or H.265 video and an AAC / MP3 audio track; audio wav or mp3. Anything else (Matroska .mkv / .mka / .webm, .m4a, VP9 / AV1) is rejected with 400 (code 20003) naming the entry — the check reads the file itself, so the URL's extension does not matter.

bitrate_mode — enum, default "default"

Available across Seedance 2.0, Fast, Mini, and 2.5, including all channels. This is reAPI output processing after generation.

• "default" or omitted: return the original file without processing or re-encoding. This is the default setting.
• "standard": compress for smaller files and faster downloads.
• "high": apply lighter compression to retain more detail than standard, usually producing a larger file. It does not enhance the original video.

Processing preserves resolution, frame timing, audio, and the MP4/MOV container. If encoding would increase file size, the original file is kept. The generation charge is unchanged. Processing adds time and supports source files up to 1 GiB; savings vary by video.

Legacy booleans remain accepted: false maps to "default", and true maps to "standard". Other values return 400 before charging. Processing or storage failures follow the existing task failure/refund policy; an unprocessed source URL is not silently substituted after a processing failure.

{ "bitrate_mode": "default" }

Modes

Mode is implicit — selected by which inputs you send:

// I2V — animate a first frame
{ "model": "seedance-2.0-mini", "first_frame_url": "https://…/frame.jpg", "resolution": "720p", "duration": 5 }

// R2V — keep subjects consistent across the clip
{ "model": "seedance-2.0-mini", "prompt": "the woman walks through the plaza", "reference_image_urls": ["https://…/a.jpg", "https://…/b.jpg"], "resolution": "720p", "duration": 5 }

More examples

curl https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer rk_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0-mini",
    "first_frame_url": "https://example.com/frame.jpg",
    "resolution": "720p",
    "duration": 5
  }'

curl https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer rk_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0-mini",
    "prompt": "the subject walks through a neon-lit street at night",
    "reference_image_urls": [
      "https://example.com/a.jpg",
      "https://example.com/b.jpg"
    ],
    "resolution": "720p",
    "duration": 5
  }'

Pricing

Per-second, billed by resolution × whether a reference video is uploaded. A request that carries reference_video_urls bills at a cheaper reference tier. See current 480p / 720p rates on the model page.

Bill formula (1 credit = $0.001):

Final bill: ceil(per_second_usd × billable_seconds × 1000) credits. Failed jobs refund automatically.

Output

On success, GET /api/v1/tasks/{id} returns:

{
  "id": "task_…",
  "model": "seedance-2.0-mini",
  "status": "completed",
  "output": { "video_urls": ["https://cdn.reapi.ai/media/tasks/…/0.mp4"] },
  "error": null
}

Errors

Pattern-match on the numeric code, not the message string. Failed generations are surfaced under error in the polling response and are refunded automatically. Full catalog: Errors.

Tips

• Pick the mode by inputs, not a flag. Sending reference_image_urls switches to R2V; sending first_frame_url switches to I2V; neither → T2V.
• Seedance 2.0 Mini is the low-cost tier — for higher resolutions (1080p / 4k) use seedance-2-0 or its official channel.
• Longer duration scales the bill linearly; start at 5s while iterating.

Related

• seedance-2-0 — full reference
• seedance-2-0-official — Official channel
• Tasks — universal polling endpoint
• Errors — full error catalog