> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# BytePlus Ark

> BytePlus Ark provides regional language, vision, image, embedding, file, response, and asynchronous video generation APIs. Chat and image generation support Johor and Dublin; the other actions require Johor.

![BytePlus Ark logo](https://mintcdn.com/composio-preview/PudKL42NVsy5O-ND/images/toolkits/byte_plus_ark.svg?fit=max\&auto=format\&n=PudKL42NVsy5O-ND\&q=85\&s=a752b01315bb890f18442281ff5a485f)

* **Category:** ai models
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 17
* **Triggers:** 0
* **Slug:** `BYTE_PLUS_ARK`
* **Version:** 20261101\_00

## Tools

> [accordion] 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. Requires a Johor (ap-southeast-1) connection and is unavailable in Dublin (eu-west-1).
>
> #### Input Parameters
>
> **task\_id** `string` *required*
>
> ID of the queued task to cancel or terminal task record to permanently delete.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Count Message Tokens
>
> **Slug:** `BYTE_PLUS_ARK_COUNT_MESSAGE_TOKENS`
>
> Count input tokens for a BytePlus Ark Anthropic-compatible Messages request without generating a model response. Requires a Johor (ap-southeast-1) connection and is unavailable in Dublin (eu-west-1).
>
> #### Input Parameters
>
> **model** `string` *required*
>
> BytePlus Ark model or inference endpoint ID whose tokenizer should be used.
>
> **tools** `array`
>
> Tool definitions whose framing should be counted.
>
> **top\_p** `number`
>
> Nucleus-sampling probability included in request framing.
>
> **system** `string`
>
> System prompt to include in the token count.
>
> **messages** `array` *required*
>
> Complete ordered conversation to include in the token count.
>
> **metadata** `object`
>
> Request metadata included in request framing.
>
> **thinking** `object`
>
> Extended-thinking configuration to include in the count.
>
> **max\_tokens** `integer`
>
> Maximum output tokens represented in request framing.
>
> **temperature** `number`
>
> Sampling temperature from 0 through 2 included in request framing.
>
> **tool\_choice** `object`
>
> Tool-selection configuration to include in request framing.
>
> **service\_tier** `string ("default" | "flex")`
>
> Online inference service tier included in request framing.
>
> **output\_config** `object`
>
> Output configuration included in request framing.
>
> **stop\_sequence** `string`
>
> One stop sequence included in request framing.
>
> **system\_blocks** `array`
>
> System content blocks to include in the token count.
>
> **stop\_sequences** `array`
>
> Up to four stop sequences included in request framing.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Chat Completion
>
> **Slug:** `BYTE_PLUS_ARK_CREATE_CHAT_COMPLETION`
>
> Generate one synchronous chat completion from an activated BytePlus Ark model or inference endpoint in the connected Johor or Dublin region. Text, vision, video, audio, file, reasoning, and tool support varies by model. Streaming is intentionally unavailable because the action runner expects one JSON response.
>
> #### Input Parameters
>
> **stop** `string`
>
> One model-supported stop sequence. Prefer stop\_sequences when passing multiple values.
>
> **model** `string` *required*
>
> Activated model ID or inference endpoint ID in the connected region. Parameter and modality support varies by model.
>
> **tools** `array`
>
> Functions available for the model to call.
>
> **top\_p** `number`
>
> Nucleus sampling threshold from 0 through 1.
>
> **logprobs** `boolean`
>
> Whether to return output-token log probabilities.
>
> **messages** `array` *required*
>
> Conversation history in chronological order.
>
> **thinking** `object`
>
> Deep-reasoning configuration for supported models.
>
> **logit\_bias** `object`
>
> Token ID to bias mapping; values must be from -100 through 100.
>
> **max\_tokens** `integer`
>
> Maximum answer tokens; model limits vary.
>
> **temperature** `number`
>
> Sampling temperature from 0 through 2.
>
> **tool\_choice** `string`
>
> Tool-selection policy: none, auto, or required. Use forced\_function\_name to require a specific function.
>
> **service\_tier** `string ("fast" | "auto" | "default" | "flex")`
>
> Requested inference service tier.
>
> **top\_logprobs** `integer`
>
> Most likely tokens to return per position (0-20).
>
> **stop\_sequences** `array`
>
> One or more model-supported stop sequences.
>
> **response\_format** `object`
>
> Text, JSON object, or JSON Schema response configuration.
>
> **presence\_penalty** `number`
>
> Presence penalty from -2 through 2.
>
> **prompt\_cache\_key** `string`
>
> Stable cache-routing identifier for related prompts.
>
> **reasoning\_effort** `string ("none" | "minimal" | "low" | "medium" | "high" | "xhigh" | "max")`
>
> Reasoning depth for supported models.
>
> **frequency\_penalty** `number`
>
> Frequency penalty from -2 through 2.
>
> **parallel\_tool\_calls** `boolean`
>
> Whether the model may request multiple tools in one response.
>
> **forced\_function\_name** `string`
>
> Name of the specific available function the model must call.
>
> **max\_completion\_tokens** `integer`
>
> Maximum answer plus reasoning tokens; cannot be combined with max\_tokens.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Message
>
> **Slug:** `BYTE_PLUS_ARK_CREATE_MESSAGE`
>
> Generate one complete, non-streaming message through BytePlus Ark's official Anthropic-compatible Messages API. Requires a Johor (ap-southeast-1) connection and is unavailable in Dublin (eu-west-1).
>
> #### Input Parameters
>
> **model** `string` *required*
>
> BytePlus Ark model or inference endpoint ID.
>
> **tools** `array`
>
> Anthropic-compatible tool definitions available to the model.
>
> **top\_p** `number`
>
> Nucleus-sampling probability from 0 through 1.
>
> **system** `string`
>
> System prompt as text.
>
> **messages** `array` *required*
>
> Complete ordered conversation history.
>
> **metadata** `object`
>
> Request metadata accepted by the compatible Messages API.
>
> **thinking** `object`
>
> Extended-thinking configuration supported by the model.
>
> **max\_tokens** `integer`
>
> Maximum output tokens to generate.
>
> **temperature** `number`
>
> Sampling temperature from 0 through 2.
>
> **tool\_choice** `object`
>
> Anthropic-compatible tool-selection configuration.
>
> **service\_tier** `string ("default" | "flex")`
>
> Online inference service tier.
>
> **output\_config** `object`
>
> Output configuration, including supported reasoning effort.
>
> **stop\_sequence** `string`
>
> One text sequence that stops generation.
>
> **system\_blocks** `array`
>
> System prompt as supported content blocks; use system for plain text.
>
> **stop\_sequences** `array`
>
> Up to four text sequences that stop generation.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Multimodal Embedding
>
> **Slug:** `BYTE_PLUS_ARK_CREATE_MULTIMODAL_EMBEDDING`
>
> Create one semantic embedding from mixed text, image, and supported video inputs using an activated skylark-embedding-vision model. Video input, sparse output, dimensions, and input combinations depend on the model version. Requires a Johor (ap-southeast-1) connection and is unavailable in Dublin (eu-west-1).
>
> #### Input Parameters
>
> **input** `array` *required*
>
> Text, image, and model-supported video inputs embedded together.
>
> **model** `string` *required*
>
> Activated skylark-embedding-vision model ID or endpoint ID in the connected region. Video, dimensions, and mixed-input limits depend on model version.
>
> **dimensions** `integer ("1024" | "2048")`
>
> Dense vector dimension; supported by model versions 250615 and later.
>
> **instructions** `string`
>
> Optional inference instruction for the embedding model.
>
> **encoding\_format** `string ("float" | "base64")`
>
> Return the dense vector as floats or Base64.
>
> **sparse\_embedding** `object`
>
> Sparse-vector output configuration; pure text input only.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] 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. Requires a Johor (ap-southeast-1) connection and is unavailable in Dublin (eu-west-1).
>
> #### Input Parameters
>
> **seed** `integer`
>
> Generation seed from -1 through 2,147,483,647; use -1 or omit it for provider-selected randomness. Supported by Seedance 1.5 pro and Seedance 1.0 models, not Seedance 2.5.
>
> **draft** `boolean`
>
> Whether to create a draft task; supported only by applicable models.
>
> **model** `string` *required*
>
> Video-generation model ID or configured inference endpoint ID available in the connected region. This free-form ID does not make this action validate model-specific parameter compatibility.
>
> **ratio** `string ("16:9" | "4:3" | "1:1" | "3:4" | "9:16" | "21:9" | "adaptive")`
>
> Requested aspect ratio, such as 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, or adaptive; support depends on the model. Seedance 2.5 requires adaptive for editing, extension, and first-frame image modes.
>
> **frames** `integer`
>
> Requested frame count from 29 through 289 matching 25 + 4n; supported by Seedance 1.0 pro and pro fast, not Seedance 2.5. This value takes precedence over duration.
>
> **content** `array` *required*
>
> Ordered model inputs. Seedance 2.5 supports an optional text item plus up to 50 total references: at most 30 reference images, 10 reference videos, and 10 reference audio clips. Other models have lower limits and different supported combinations; this schema caps total items but does not infer compatibility from the free-form model ID.
>
> **duration** `integer`
>
> Requested video duration in seconds; allowed ranges are model-dependent. Seedance 2.5 supports 4-30 or -1, and editing requires -1. frames takes precedence when both are supplied.
>
> **priority** `integer`
>
> Queue priority from 0 through 9 for Seedance 2.5 and Seedance 2.0 models; larger values run first within the same endpoint. Not supported with flex.
>
> **watermark** `boolean`
>
> Whether to add the provider watermark to the generated video.
>
> **resolution** `string ("480p" | "720p" | "1080p")`
>
> Requested output resolution, commonly 480p, 720p, or 1080p; supported values and defaults depend on the model.
>
> **callback\_url** `string`
>
> HTTPS endpoint to receive provider POST callbacks when task status changes. Omit it to avoid callback side effects.
>
> **camera\_fixed** `boolean`
>
> Whether to request a fixed camera. Supported by Seedance 1.5 pro and Seedance 1.0 models, not Seedance 2.5, and unavailable for reference-image scenarios.
>
> **service\_tier** `string ("default" | "flex")`
>
> Execution tier: default for online processing or flex for supported lower-cost offline processing. Seedance 2.5 and Seedance 2.0 models do not support flex.
>
> **output\_format** `string ("mp4" | "mov")`
>
> Seedance 2.5 output container: mp4 (default, broad compatibility) or mov (high color precision for professional workflows). Omit for other models.
>
> **generate\_audio** `boolean`
>
> Whether to generate audio with the video; omit this to use the selected model's native default.
>
> **return\_last\_frame** `boolean`
>
> Whether the completed task should include a last-frame image URL.
>
> **safety\_identifier** `string`
>
> Stable privacy-preserving end-user identifier of no more than 64 characters; BytePlus recommends English characters.
>
> **execution\_expires\_after** `integer`
>
> Seconds the queued task may wait before expiring (3,600-259,200).
>
> **omni\_reference\_task\_type** `string ("reference" | "edit" | "extend" | "auto")`
>
> Seedance 2.5 omni-reference task hint. auto lets the model infer the task and can fail asynchronously for incompatible parameters. Explicit reference, edit, or extend enables earlier API constraint checks, but the task can still fail asynchronously if the prompt implies a different type. edit requires a 4-30 second reference video and uses ratio=adaptive and duration=-1 by default; extend requires a reference video and uses ratio=adaptive by default. Omit for other models.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete File
>
> **Slug:** `BYTE_PLUS_ARK_DELETE_FILE`
>
> Permanently delete a BytePlus Ark file from storage. The file cannot be restored or used by later model inference requests. Requires a Johor (ap-southeast-1) connection and is unavailable in Dublin (eu-west-1).
>
> #### Input Parameters
>
> **file\_id** `string` *required*
>
> ID of the file to permanently delete.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Response
>
> **Slug:** `BYTE_PLUS_ARK_DELETE_RESPONSE`
>
> Permanently delete one stored BytePlus Ark Responses API object by ID. Requires a Johor (ap-southeast-1) connection and is unavailable in Dublin (eu-west-1).
>
> #### Input Parameters
>
> **response\_id** `string` *required*
>
> Stored response ID to permanently delete.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Generate Image
>
> **Slug:** `BYTE_PLUS_ARK_GENERATE_IMAGE`
>
> Generate or edit images synchronously with an activated Seedream model in the connected Johor or Dublin region. Image counts, reference limits, dimensions, prompt optimization, sequences, transparency, and layer decomposition are model-specific. Streaming is intentionally unavailable. This operation is billable.
>
> #### Input Parameters
>
> **size** `string`
>
> Resolution label or widthxheight; valid ranges depend on the Seedream model.
>
> **image** `string`
>
> Accessible image URL or data URL for a single reference image.
>
> **model** `string` *required*
>
> Activated Seedream model ID or inference endpoint ID in the connected region. Size, editing, decomposition, and sequence support varies by model.
>
> **tools** `array`
>
> Model-supported content-generation tools such as web search.
>
> **images** `array`
>
> Model-supported list of reference image URLs or data URLs.
>
> **prompt** `string`
>
> Generation or editing prompt; optional only for automatic layer decomposition.
>
> **watermark** `boolean`
>
> Whether to add the provider's AI-generated watermark.
>
> **background** `string ("transparent" | "opaque")`
>
> Background mode for supported single-image alpha-channel edits.
>
> **output\_format** `string ("png" | "jpeg")`
>
> Generated image file format for supported models.
>
> **optimize\_prompt** `boolean`
>
> Whether to apply provider prompt optimization.
>
> **response\_format** `string ("url" | "b64_json")`
>
> Return temporary URLs or Base64-encoded image data.
>
> **layer\_decomposition** `boolean`
>
> Decompose one image into a base image and layers; Seedream 5.0 pro/flash only.
>
> **optimize\_prompt\_options** `object`
>
> Prompt optimization settings.
>
> **sequential\_image\_generation** `string ("auto" | "disabled")`
>
> Generate a related image sequence on Seedream 5.0 lite, 4.5, or 4.0.
>
> **sequential\_image\_generation\_options** `object`
>
> Sequential generation limits.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get File
>
> **Slug:** `BYTE_PLUS_ARK_GET_FILE`
>
> Retrieve one BytePlus Ark file's metadata, preprocessing status, expiration, and failure details by file ID. Requires a Johor (ap-southeast-1) connection and is unavailable in Dublin (eu-west-1).
>
> #### Input Parameters
>
> **file\_id** `string` *required*
>
> BytePlus Ark file ID returned by upload or list.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Response
>
> **Slug:** `BYTE_PLUS_ARK_GET_RESPONSE`
>
> Retrieve a stored BytePlus Ark Responses API object by ID, including its status, output, configuration, and token usage. Requires a Johor (ap-southeast-1) connection and is unavailable in Dublin (eu-west-1).
>
> #### Input Parameters
>
> **response\_id** `string` *required*
>
> Response ID returned by the Responses API.
>
> **include\_image\_urls** `boolean`
>
> Include source image URLs in returned message input-image items.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] 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. Requires a Johor (ap-southeast-1) connection and is unavailable in Dublin (eu-west-1).
>
> #### Input Parameters
>
> **task\_id** `string` *required*
>
> Video generation task ID returned by create or list.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Files
>
> **Slug:** `BYTE_PLUS_ARK_LIST_FILES`
>
> Return one cursor-paginated page of BytePlus Ark files, optionally filtered by purpose or Managed Agents session scope. Requires a Johor (ap-southeast-1) connection and is unavailable in Dublin (eu-west-1).
>
> #### Input Parameters
>
> **after** `string`
>
> File ID cursor returned as next\_cursor by a previous call. Omit it for the first page.
>
> **limit** `integer`
>
> Maximum files to return in this page (1-100).
>
> **order** `string ("asc" | "desc")`
>
> Sort by creation time in ascending or descending order.
>
> **purpose** `string ("user_data" | "agent")`
>
> Return only files with this purpose.
>
> **scope\_id** `string`
>
> Managed Agents session ID whose mounted and generated files to return.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Response Input Items
>
> **Slug:** `BYTE_PLUS_ARK_LIST_RESPONSE_INPUT_ITEMS`
>
> Return one page of the input context associated with a BytePlus Ark response, with forward or backward ID pagination. Requires a Johor (ap-southeast-1) connection and is unavailable in Dublin (eu-west-1).
>
> #### Input Parameters
>
> **after** `string`
>
> Return items after this input item ID.
>
> **limit** `integer`
>
> Maximum items to return (1-100).
>
> **order** `string ("asc" | "desc")`
>
> Sort order by item creation time.
>
> **before** `string`
>
> Return items before this input item ID.
>
> **response\_id** `string` *required*
>
> Response ID whose input context should be listed.
>
> **include\_image\_urls** `boolean`
>
> Include source image URLs in returned message input-image items.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] 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. Requires a Johor (ap-southeast-1) connection and is unavailable in Dublin (eu-west-1).
>
> #### Input Parameters
>
> **model** `string`
>
> Return only tasks created with this exact model or inference endpoint ID.
>
> **status** `string ("queued" | "running" | "cancelled" | "succeeded" | "failed")`
>
> Return only tasks with this status.
>
> **page\_num** `integer`
>
> Page number to return (1-500); increment it to request the next page.
>
> **task\_ids** `array`
>
> Return only these task IDs. Each ID is sent as a separate repeated filter.task\_ids query parameter.
>
> **page\_size** `integer`
>
> Maximum number of tasks to return in this page (1-500).
>
> **service\_tier** `string ("default" | "flex")`
>
> Return only tasks using the default or flex service tier.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Tokenize Text
>
> **Slug:** `BYTE_PLUS_ARK_TOKENIZE_TEXT`
>
> Tokenize text with an activated BytePlus Ark text model or inference endpoint This endpoint accepts text only; token vocabulary and model availability are model- and region-specific. Requires a Johor (ap-southeast-1) connection and is unavailable in Dublin (eu-west-1).
>
> #### Input Parameters
>
> **text** `string`
>
> A single text string to tokenize; use texts for multiple strings.
>
> **model** `string` *required*
>
> Activated text model ID or inference endpoint ID in the connected region. The tokenization endpoint currently supports text input only.
>
> **texts** `array`
>
> Multiple text strings to tokenize in one request; use text for one string.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Upload File
>
> **Slug:** `BYTE_PLUS_ARK_UPLOAD_FILE`
>
> Upload a local file or import an HTTP(S) or BytePlus TOS file into BytePlus Ark for model or agent use. Files expire automatically; video preprocessing may continue after this request returns. Requires a Johor (ap-southeast-1) connection and is unavailable in Dublin (eu-west-1).
>
> #### Input Parameters
>
> **url** `string`
>
> Public HTTP(S) URL or BytePlus TOS URI. Use either url or file, not both.
>
> **file** `object`
>
> A local file supplied for upload to BytePlus Ark.
>
> **purpose** `string ("user_data" | "agent")` *required*
>
> File purpose: user\_data for general model input or agent for agent files.
>
> **expire\_at** `integer`
>
> UTC Unix expiration timestamp. It must be 1-30 days from upload time; omit it for the provider's 7-day default.
>
> **tos\_bucket** `string`
>
> Existing BytePlus TOS bucket used to store the uploaded file.
>
> **tos\_prefix** `string`
>
> Relative path prefix in the TOS bucket, such as arkfiles/.
>
> **preprocess\_video\_fps** `number`
>
> Video frame sampling rate per second (0.2-5).
>
> **preprocess\_video\_model** `string`
>
> Model or inference endpoint ID used to choose video frame sampling defaults.
>
> **preprocess\_video\_max\_tokens** `integer`
>
> Maximum video preprocessing token budget (10,240-204,800).
>
> **preprocess\_video\_min\_frames** `integer`
>
> Minimum sampled frame count for short videos (5-16).
>
> **preprocess\_video\_max\_frame\_tokens** `integer`
>
> Maximum token budget per sampled frame (128-640).
>
> **preprocess\_video\_min\_frame\_tokens** `integer`
>
> Minimum token budget per sampled frame (16-128).
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
