---
canonical_url: "https://docs.composio.dev/toolkits/byte_plus_ark"
markdown_url: "https://docs.composio.dev/toolkits/byte_plus_ark.md"
product: "platform"
version: null
last_updated: null
---

# BytePlus Ark

BytePlus Ark provides regional generative AI model APIs, including asynchronous video generation task creation, status retrieval, listing, cancellation, and deletion.

- **Category:** ai models
- **Auth:** API_KEY
- **Composio-managed OAuth available?** N/A
- **Tools:** 4
- **Triggers:** 0
- **Slug:** `BYTE_PLUS_ARK`
- **Version:** 00000000_00

## Tools

### Cancel or Delete Video Task

**Slug:** `BYTE_PLUS_ARK_CANCEL_OR_DELETE_VIDEO_TASK`

Irreversibly cancel a video generation task when it is queued, or permanently delete its task record when it is terminal. BytePlus Ark chooses the effect from the task's current status; the caller cannot select cancel versus delete. Check the task with Get Video Task first and use only an intended disposable task.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `task_id` | string | Yes | ID of the queued task to cancel or terminal task record to permanently delete. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create Video Task

**Slug:** `BYTE_PLUS_ARK_CREATE_VIDEO_TASK`

Start a potentially billable asynchronous video generation task and return its task ID. Model capabilities and optional parameter support vary. A callback URL, if supplied, may receive task-status POSTs.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `seed` | integer | No | Generation seed from -1 through 4,294,967,295; use -1 or omit it for provider-selected randomness. |
| `draft` | boolean | No | Whether to create a draft task; supported only by applicable models. |
| `model` | string | Yes | Video-generation model ID or configured inference endpoint ID available in the connected region. |
| `ratio` | string ("16:9" | "4:3" | "1:1" | "3:4" | "9:16" | "21:9" | "adaptive") | No | Requested aspect ratio, such as 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, or adaptive; support depends on the model. |
| `frames` | integer | No | Requested frame count from 29 through 289 matching 25 + 4n; model support varies, and this value takes precedence over duration. |
| `content` | array | Yes | One to five ordered model inputs. Supported input combinations and roles depend on the selected model. |
| `duration` | integer | No | Requested video duration in seconds; allowed ranges are model-dependent. frames takes precedence when both are supplied. |
| `priority` | integer | No | Optional scheduling priority supported by some SDK and model combinations; provider limits are not documented. |
| `watermark` | boolean | No | Whether to add the provider watermark to the generated video. |
| `resolution` | string ("480p" | "720p" | "1080p") | No | Requested output resolution, commonly 480p, 720p, or 1080p; supported values and defaults depend on the model. |
| `callback_url` | string | No | HTTPS endpoint to receive provider POST callbacks when task status changes. Omit it to avoid callback side effects. |
| `camera_fixed` | boolean | No | Whether to request a fixed camera; availability depends on the model and input mode. |
| `service_tier` | string ("default" | "flex") | No | Execution tier: default for online processing or flex for supported lower-cost offline processing. |
| `output_format` | string | No | Optional output format supported by some SDK and model combinations; accepted values are model-dependent. |
| `generate_audio` | boolean | No | Whether to generate audio with the video; omit this to use the selected model's native default. |
| `return_last_frame` | boolean | No | Whether the completed task should include a last-frame image URL. |
| `safety_identifier` | string | No | Stable privacy-preserving end-user identifier of no more than 64 characters; BytePlus recommends English characters. |
| `execution_expires_after` | integer | No | Seconds the queued task may wait before expiring (3,600-259,200). |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Video Task

**Slug:** `BYTE_PLUS_ARK_GET_VIDEO_TASK`

Retrieve one video generation task's status, failure details, and generated output URLs by task ID.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `task_id` | string | Yes | Video generation task ID returned by create or list. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Video Tasks

**Slug:** `BYTE_PLUS_ARK_LIST_VIDEO_TASKS`

Return one page of video generation tasks, optionally filtered by status, task IDs, model, or service tier.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `model` | string | No | Return only tasks created with this exact inference endpoint ID. |
| `status` | string ("queued" | "running" | "cancelled" | "succeeded" | "failed") | No | Return only tasks with this status. |
| `page_num` | integer | No | Page number to return, starting at 1; increment it to request the next page. |
| `task_ids` | array | No | Return only these task IDs. Each ID is sent as a separate repeated filter.task_ids query parameter. |
| `page_size` | integer | No | Maximum number of tasks to return in this page (1-500). |
| `service_tier` | string ("default" | "flex") | No | Return only tasks using the default or flex service tier. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |