Open API v1 · Vidrush V1

Put AI video generation behind your product

The Vidrush Open API is an asynchronous generation gateway. Create returns a task immediately, the website and API share one credit ledger, and every public video model — Vidrush V1, Seedance 2.0, Veo 3.1, Kling 2.6, MiniMax H3 and more — sits behind the same request shape. Images, music, speech and sound effects ride the same task lifecycle.

Text-to-Video: generate from a prompt alone.
Image-to-Video / Frames-to-Video: animate one image, or bridge a first and last frame.
Reference-to-Video / Video-to-Video: keep identity from reference images or restyle an existing clip.

Get an API key See the workflow

Quickstart

Any signed-in user can create an sk_ key under Settings → API Keys. The secret is shown once — store it on your server.

1
Set environment variables
Every request is sent to the base URL with the key as a Bearer token.
SHELL
```
export VIDRUSH_BASE_URL=https://vidrush-ai.com/api/v1
export VIDRUSH_API_KEY=sk-xxx
```
2
Quote credits (optional, free)
POST the same body to /videos/quote and read data.costCredits. Quote and create share one billing formula.
3
Create the task
POST /videos. Success is 200 with the task object; data.id is your handle and data.costCredits is what was charged.
4
Poll the task
GET /tasks/{id} every 5 seconds until status is success, failed or canceled. On success, play the URLs in data.taskUrls.

Authentication

Authorizationstring · headerrequired

Every endpoint requires Authorization: Bearer $VIDRUSH_API_KEY. Keys are created and revoked under Settings → API Keys and inherit the account's credit balance.

Content-Typestring · headerrequired

application/json on every POST. Request bodies are plain JSON objects; arrays of URLs must be public HTTPS.

Response envelope

Every response is {"code", "message", "data"}. code 0 is success and data carries the payload; non-zero code plus an HTTP error status means the request did not go through. Branch on the HTTP status and code, not the message text.

200 · GET /credits

{
  "code": 0,
  "message": "ok",
  "data": {
    "remainingCredits": 1240
  }
}

Models and capabilities

GET/api/v1/modelsendpoint

Returns the public models available right now — durations, resolutions, aspect ratios, audio toggle and credit pricing per mode. This is the live source of truth; the table below is rendered from the same catalog.

?type=video|image|music — type selects the catalog: video (default), image or music. Responses are cacheable for an hour.

21 public video models

Model ID	Vendor	Modes	Durations	Resolutions	Credits
p-video	Pruna AI	text-to-videoimage-to-video	1s – 20s	720p · 1080p	4-160 credits
seedance-2-0	ByteDance	text-to-videoimage-to-videoframes-to-videoreference-to-video	4s – 15s	480p · 720p · 1080p · 4k	60-3270 credits
seedance-2-0-fast	ByteDance	text-to-videoimage-to-videoframes-to-videoreference-to-video	4s – 15s	480p · 720p	42-420 credits
seedance-2-mini	ByteDance	text-to-videoimage-to-videoframes-to-videoreference-to-video	4s – 15s	480p · 720p	16-150 credits
seedance-1-5-pro	ByteDance	text-to-videoimage-to-video	4s – 12s	480p · 720p · 1080p	7-60 credits
grok-imagine	Grok	text-to-videoimage-to-video	6s – 30s	480p · 720p	10-90 credits
grok-imagine-1-5	Grok	text-to-videoimage-to-video	6s – 30s	480p · 720p	18-90 credits
kling-2-6	Kling	text-to-videoimage-to-video	5s – 10s	—	55-220 credits
runway	Runway	text-to-videoimage-to-video	5s – 10s	720p · 1080p	12-30 credits
veo-3-1	Google	text-to-videoimage-to-videoframes-to-videoreference-to-video	—	720p · 1080p · 4k	225-285 credits
veo-3-1-fast	Google	text-to-videoimage-to-videoframes-to-videoreference-to-video	—	720p · 1080p · 4k	30-100 credits
veo-3-1-lite	Google	text-to-videoimage-to-videoframes-to-videoreference-to-video	—	720p · 1080p · 4k	15-75 credits
gemini-omni-cheap	Google	text-to-videoimage-to-videovideo-to-video	10s	720p	35 credits
gemini-omni	Google	text-to-videoimage-to-videovideo-to-video	10s	720p · 1080p	50 credits
gemini-omni-video	Google	text-to-videoimage-to-videovideo-to-video	4s – 10s	720p · 1080p · 4k	45-180 credits
flux-3	Black Forest Labs	text-to-videoimage-to-videovideo-to-videoframes-to-video	5s – 20s	—	80-320 credits
minimax-h3	MiniMax	text-to-videoimage-to-videoreference-to-video	4s – 15s	768P · 2K	72-435 credits
seedence-1-0-pro	ByteDance	text-to-videoimage-to-video	5s – 10s	480p · 720p · 1080p	14-42 credits
seedence-1-0-pro-fast	ByteDance	image-to-video	5s – 10s	720p · 1080p	16+ credits
seedence-1-0-lite	ByteDance	text-to-videoimage-to-video	5s – 10s	480p · 720p · 1080p	10-40 credits
vidrush-v1	VidRush	text-to-videoimage-to-videoframes-to-videoreference-to-video	1s – 15s	480p · 768P	1-15 credits

200 · GET /models

{
  "code": 0,
  "message": "ok",
  "data": {
    "models": [
      {
        "id": "vidrush-v1",
        "label": "Vidrush V1",
        "vendor": "VidRush",
        "modes": {
          "text-to-video": {
            "durations": [
              "1s",
              "2s",
              "3s",
              "4s",
              "5s",
              "6s",
              "7s",
              "8s",
              "9s",
              "10s",
              "11s",
              "12s",
              "13s",
              "14s",
              "15s"
            ],
            "resolutions": [
              "480p",
              "768P"
            ],
            "aspect_ratios": [
              "16:9",
              "9:16"
            ],
            "audio_toggle": false,
            "credits_per_second": {
              "480p": 1,
              "768P": 1
            }
          },
          "image-to-video": {
            "durations": [
              "1s",
              "2s",
              "3s",
              "4s",
              "5s",
              "6s",
              "7s",
              "8s",
              "9s",
              "10s",
              "11s",
              "12s",
              "13s",
              "14s",
              "15s"
            ],
            "resolutions": [
              "480p",
              "768P"
            ],
            "aspect_ratios": [
              "16:9",
              "9:16"
            ],
            "audio_toggle": false,
            "credits_per_second": {
              "480p": 1,
              "768P": 1
            }
          },
          "frames-to-video": {
            "durations": [
              "1s",
              "2s",
              "3s",
              "4s",
              "5s",
              "6s",
              "7s",
              "8s",
              "9s",
              "10s",
              "11s",
              "12s",
              "13s",
              "14s",
              "15s"
            ],
            "resolutions": [
              "480p",
              "768P"
            ],
            "aspect_ratios": [
              "16:9",
              "9:16"
            ],
            "audio_toggle": false,
            "credits_per_second": {
              "480p": 1,
              "768P": 1
            }
          },
          "reference-to-video": {
            "durations": [
              "1s",
              "2s",
              "3s",
              "4s",
              "5s",
              "6s",
              "7s",
              "8s",
              "9s",
              "10s",
              "11s",
              "12s",
              "13s",
              "14s",
              "15s"
            ],
            "resolutions": [
              "480p",
              "768P"
            ],
            "aspect_ratios": [
              "16:9",
              "9:16"
            ],
            "audio_toggle": false,
            "credits_per_second": {
              "480p": 1,
              "768P": 1
            }
          }
        },
        "credits_label": "1-15 credits"
      },
      "…"
    ]
  }
}

Quote a generation

POST/api/v1/videos/quoteendpoint

Use the exact body you would send to create. Nothing is created and no credits move; you get back the model, mode and costCredits that create would charge.

200 · POST /videos/quote

{
  "code": 0,
  "message": "ok",
  "data": {
    "model": "vidrush-v1",
    "mode": "text-to-video",
    "costCredits": 5
  }
}

Quote first, then decide whether the user can submit — combine it with GET /credits for a balance check.

Create a video generation

POST/api/v1/videosendpoint

Creates an asynchronous video task, charges costCredits up front, and returns the task object. Use the monitor on the right to switch model, mode and language.

modelstringrequired

A current model ID from GET /models. Use the public IDs shown in the table above, not upstream aliases.

promptstringrequired

Non-empty video instruction. Describe subject, action, camera and style; the model receives it verbatim.

modeenum

text-to-video, image-to-video, frames-to-video, reference-to-video or video-to-video; must be supported by the model. Defaults to text-to-video, or image-to-video when image_urls is present.

image_urlsstring[]

Public HTTPS image URLs. image-to-video takes one, frames-to-video takes first and last, reference-to-video takes up to the model's slot count.

video_urlsstring[]

Public HTTPS video URLs for video-to-video models. Send options.source_video_duration_seconds when the model is priced per second.

optionsobject

Model-specific controls. Only send values the selected model and mode advertise in GET /models.

options

field	type	description
duration	string	A supported duration such as "5s" or "10s".
resolution	string	A supported resolution such as "720p", "768P" or "1080p".
aspect_ratio	string	A supported ratio such as "16:9", "9:16" or "Auto".
audio	boolean	Only when the model/mode exposes audio_toggle: true.
source_video_duration_seconds	number	Required with video_urls on per-second-priced models.

200 · POST /videos

{
  "code": 0,
  "message": "ok",
  "data": {
    "id": "task_01JQ9X2B6XK9K4VQY2QZ4H6W3R",
    "userId": "user_1",
    "mediaType": "video",
    "model": "vidrush-v1",
    "scene": "text-to-video",
    "status": "pending",
    "costCredits": 5,
    "taskId": null,
    "taskUrls": [],
    "createdAt": "2026-09-07T12:00:00.000Z",
    "updatedAt": "2026-09-07T12:00:00.000Z"
  }
}

The task record is sanitized before it is returned: provider names, internal prompts and request fingerprints are never exposed.

Get a task

GET/api/v1/tasks/{taskId}endpoint

Poll until status is success, failed or canceled. The response is the same sanitized task object create returned, refreshed from the provider when the task is still in flight.

Status lifecycle

status
pending	Accepted and queued. Keep polling.
processing	The provider is generating. Keep polling.
success	Done. Play or download the URLs in data.taskUrls.
failed	Generation failed. Credits were refunded automatically.
canceled	The provider canceled the job. Credits were refunded automatically.

200 · GET /tasks/{taskId}

{
  "code": 0,
  "message": "ok",
  "data": {
    "id": "task_01JQ9X2B6XK9K4VQY2QZ4H6W3R",
    "userId": "user_1",
    "mediaType": "video",
    "model": "vidrush-v1",
    "scene": "text-to-video",
    "status": "success",
    "costCredits": 5,
    "taskId": "prov_8f1c",
    "taskUrls": [
      "https://r2.vibevideo.app/vidrush/videos/task_01JQ9X2B.mp4"
    ],
    "createdAt": "2026-09-07T12:00:00.000Z",
    "updatedAt": "2026-09-07T12:02:41.000Z"
  }
}

Poll every 5 seconds. Result URLs are platform URLs, not upstream temporary links, so they are safe to store.

List tasks

GET/api/v1/tasksendpoint

Your own tasks, newest first, in the same sanitized shape as GET /tasks/{id}.

statusenum

pending, processing, success, failed or canceled.

media_typeenum

video, image, music, audio or speech.

pageinteger

1-based page, default 1.

limitinteger

1–100, default 20. data.has_more tells you whether to fetch the next page.

200 · GET /tasks?limit=20

{
  "code": 0,
  "message": "ok",
  "data": {
    "tasks": [
      {
        "id": "task_01JQ9X2B…",
        "status": "success",
        "mediaType": "video"
      },
      {
        "id": "task_01JQ9WZ4…",
        "status": "processing",
        "mediaType": "image"
      }
    ],
    "page": 1,
    "limit": 20,
    "has_more": false
  }
}

Create an image

POST/api/v1/imagesendpoint

Text-to-image and image-to-image on the same task lifecycle. Discover models with GET /models?type=image.

modelstringrequired

A current image model ID such as nano-banana-2.

promptstringrequired

Non-empty image instruction.

sceneenum

text-to-image or image-to-image. Defaults to image-to-image when image_urls is present.

image_urlsstring[]

Public HTTPS image URLs; required for image-to-image.

optionsobject

aspect_ratio (e.g. "1:1", "16:9") and quality ("1K", "2K", "4K") as advertised by the model.

BODY · POST /images

{
  "model": "nano-banana-2",
  "prompt": "Editorial product shot of a ceramic mug on linen, soft window light",
  "options": {
    "aspect_ratio": "1:1",
    "quality": "2K"
  }
}

Speech and sound effects

Text-to-speech uses the ElevenLabs voice catalog; sound effects take a prompt. Both return a task with the audio URL in taskUrls.

POST/api/v1/speechendpoint

textstringrequired

Non-empty text to speak.

voice_idstringrequired

A voice id from GET /voices.

optionsobject

model_id, speed (0.25–4), stability (0–1), similarity_boost (0–1).

POST/api/v1/sound-effectsendpoint

promptstringrequired

Description of the sound.

optionsobject

duration_seconds (0.5–22), prompt_influence (0–1).

GET/api/v1/voicesendpoint

GET /voices returns the public voice catalog with ids, names, languages and preview URLs. No authentication is required for the catalog.

Billing

The website and API use the same prices for the same account. Credits are charged when a task is accepted and returned when it cannot be delivered.

Stage	Behavior
quote	No charge; returns costCredits.
create	Charges costCredits and returns the task.
success	The charge stands; result URLs are yours to keep.
failed / canceled	costCredits is refunded to the balance automatically.

Error handling

Branch on the HTTP status and the stable code field. 500 is safe to retry.

HTTP	code	Meaning
400	-1	Malformed body, unknown model, unsupported mode or option — the message says which.
401	-1001	Missing, invalid or revoked API key.
402	-1002	Insufficient credits for costCredits. Top up or pick a cheaper option.
404	-1	Task does not exist or belongs to another account.
500	-1	Provider or internal failure; the public message is generic. Retry.

Machine-readable:llms.txtFull guidesLast updated 2026-09-08

SOURCEtext to video · Vidrush V1

curl --request POST \
  --url $VIDRUSH_BASE_URL/videos \
  --header "Authorization: Bearer $VIDRUSH_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "vidrush-v1",
  "mode": "text-to-video",
  "prompt": "A paper kite crossing a bright summer sky, cinematic slow push-in",
  "options": {
    "duration": "8s",
    "resolution": "480p",
    "aspect_ratio": "16:9"
  }
}'

RESPONSE

{
  "code": 0,
  "message": "ok",
  "data": {
    "id": "task_01JQ9X2B6XK9K4VQY2QZ4H6W3R",
    "userId": "user_1",
    "mediaType": "video",
    "model": "vidrush-v1",
    "scene": "text-to-video",
    "status": "pending",
    "costCredits": 8,
    "taskId": null,
    "taskUrls": [],
    "createdAt": "2026-09-07T12:00:00.000Z",
    "updatedAt": "2026-09-07T12:00:00.000Z"
  }
}

LIVE

Production https://vidrush-ai.com/api/v1

SOURCEtext to video · Vidrush V1

curl --request POST \
  --url $VIDRUSH_BASE_URL/videos \
  --header "Authorization: Bearer $VIDRUSH_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "vidrush-v1",
  "mode": "text-to-video",
  "prompt": "A paper kite crossing a bright summer sky, cinematic slow push-in",
  "options": {
    "duration": "8s",
    "resolution": "480p",
    "aspect_ratio": "16:9"
  }
}'

RESPONSE

{
  "code": 0,
  "message": "ok",
  "data": {
    "id": "task_01JQ9X2B6XK9K4VQY2QZ4H6W3R",
    "userId": "user_1",
    "mediaType": "video",
    "model": "vidrush-v1",
    "scene": "text-to-video",
    "status": "pending",
    "costCredits": 8,
    "taskId": null,
    "taskUrls": [],
    "createdAt": "2026-09-07T12:00:00.000Z",
    "updatedAt": "2026-09-07T12:00:00.000Z"
  }
}

LIVE

Production https://vidrush-ai.com/api/v1

Put AI video generation behind your product

Quickstart

Integrate into your video product

Authentication

Response envelope

Models and capabilities

Quote a generation

Create a video generation

options

Get a task

Status lifecycle

List tasks

Create an image

Create music

Speech and sound effects

Credit balance

Billing

Error handling