seedance-2-0-mini

ByteDance Seedance 2.0 Mini — the low-cost tier of Seedance 2.0. One async video endpoint that auto-routes text-to-video, image-to-video, and reference-to-video by request shape, at 480p / 720p.

ByteDance Seedance 2.0 Mini — the low-cost tier of the Seedance 2.0 family. A single async video endpoint that auto-routes between T2V / I2V / R2V based on which media field your request carries. 480p or 720p, 4–15 second outputs. See current pricing on the model page.

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

URL-only media. All media inputs must be public http(s) URLs. base64 / data: URI media is not accepted by ReAPI — even where upstream docs show base64 examples.

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.

Parameters

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

Parameter	Type	Required	Default	Description
`prompt`	string	T2V: yes · I2V / R2V: no	—	Text prompt. Required for text-to-video; optional when a `first_frame_url` or `reference_image_urls` is set.
`first_frame_url`	string	I2V	—	First-frame image, a single public `http(s)` URL. Presence selects image-to-video.
`last_frame_url`	string	no	—	Optional last-frame image, a public `http(s)` URL.
`reference_image_urls`	string[]	R2V	—	1–9 reference image URLs. Presence selects reference-to-video.
`reference_video_urls`	string[]	no	—	Up to 3 reference video URLs.
`reference_audio_urls`	string[]	no	—	Up to 3 reference audio URLs.
`generate_audio`	boolean	no	`false`	Generate an audio track for the output video.
`resolution`	enum	no	`720p`	`480p` · `720p`.
`aspect_ratio`	enum	no	`16:9`	`16:9` `9:16` `1:1` `4:3` `3:4` `21:9` `adaptive`.
`duration`	integer	no	`5`	Output length in seconds, `4`–`15`.
`web_search`	boolean	no	`false`	Allow the model to ground the prompt with web search.
`nsfw_checker`	boolean	no	`true`	Run the upstream NSFW content check.

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.

Modes

Mode is implicit — selected by which inputs you send:

Mode	Trigger	prompt
Text-to-video (T2V)	no media	required
Image-to-video (I2V)	`first_frame_url` (optionally `last_frame_url`)	optional
Reference-to-video (R2V)	`reference_image_urls` (1–9)	optional

// 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):

Input	Billable seconds
No `reference_video_urls` (text / image / first-last-frame / reference-image)	`duration` you sent (default 5)
With `reference_video_urls`	`duration` + `ceil(sum of source video seconds)` — the vendor processes the input clip(s) AND produces the output; both are billable. Failed probe → `400 PRICING_UNAVAILABLE`, no charge.

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

HTTP	`code`	When
400	`20002`	Missing / invalid parameter (e.g. prompt required in T2V, value out of range)
400	`80007`	Upstream content rejection (e.g. a flagged source image)
401	`10001` – `10005`	Auth missing / invalid / revoked
402	`30001`	Insufficient credits
429	`50001`	Per-user rate limit exceeded

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.

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

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

URL-only media. All media inputs must be public http(s) URLs. base64 / data: URI media is not accepted by ReAPI — even where upstream docs show base64 examples.

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.

Parameters

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

Parameter	Type	Required	Default	Description
`prompt`	string	T2V: yes · I2V / R2V: no	—	Text prompt. Required for text-to-video; optional when a `first_frame_url` or `reference_image_urls` is set.
`first_frame_url`	string	I2V	—	First-frame image, a single public `http(s)` URL. Presence selects image-to-video.
`last_frame_url`	string	no	—	Optional last-frame image, a public `http(s)` URL.
`reference_image_urls`	string[]	R2V	—	1–9 reference image URLs. Presence selects reference-to-video.
`reference_video_urls`	string[]	no	—	Up to 3 reference video URLs.
`reference_audio_urls`	string[]	no	—	Up to 3 reference audio URLs.
`generate_audio`	boolean	no	`false`	Generate an audio track for the output video.
`resolution`	enum	no	`720p`	`480p` · `720p`.
`aspect_ratio`	enum	no	`16:9`	`16:9` `9:16` `1:1` `4:3` `3:4` `21:9` `adaptive`.
`duration`	integer	no	`5`	Output length in seconds, `4`–`15`.
`web_search`	boolean	no	`false`	Allow the model to ground the prompt with web search.
`nsfw_checker`	boolean	no	`true`	Run the upstream NSFW content check.

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.

Modes

Mode is implicit — selected by which inputs you send:

Mode	Trigger	prompt
Text-to-video (T2V)	no media	required
Image-to-video (I2V)	`first_frame_url` (optionally `last_frame_url`)	optional
Reference-to-video (R2V)	`reference_image_urls` (1–9)	optional

// 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

Bill formula (1 credit = $0.001):

Input	Billable seconds
No `reference_video_urls` (text / image / first-last-frame / reference-image)	`duration` you sent (default 5)
With `reference_video_urls`	`duration` + `ceil(sum of source video seconds)` — the vendor processes the input clip(s) AND produces the output; both are billable. Failed probe → `400 PRICING_UNAVAILABLE`, no charge.

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

HTTP	`code`	When
400	`20002`	Missing / invalid parameter (e.g. prompt required in T2V, value out of range)
400	`80007`	Upstream content rejection (e.g. a flagged source image)
401	`10001` – `10005`	Auth missing / invalid / revoked
402	`30001`	Insufficient credits
429	`50001`	Per-user rate limit exceeded

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.

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

seedance-2-0-mini

Quick example

Endpoint

Parameters

Modes

More examples

Pricing

Output

Errors

Tips

Table of Contents

seedance-2-0-mini

Quick example

Endpoint

Parameters

Modes

More examples

Pricing

Output

Errors

Tips

Table of Contents