> ## Documentation Index
> Fetch the complete documentation index at: https://testweb2-docs-openapi.test765.com/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Five API is a video generation REST API. Base URL: https://api.fiveapi.ai. Authenticate with the header Authorization: Bearer <API key>; read the key from the FIVEAPI_API_KEY environment variable and never hard-code it.
> Every generation is an asynchronous task: POST /v1/{brand}/{version}/{task} returns a queued task, then poll GET /v1/tasks/{task_id} or receive a signed webhook, and download output.video.url before expires_at (7 days).
> The OpenAPI spec is at https://docs.fiveapi.ai/api-reference/openapi.yaml. An installable agent skill: npx skills add https://docs.fiveapi.ai

# Get a task

> Returns the current state of a task. While the task is `queued`, `queue.position` shows its place in the
model's queue; once it is `completed`, `output.video.url` holds the MP4.

Poll every few seconds with backoff, or use [webhooks](/concepts/webhooks) instead. The output is removed at
`expires_at`, 7 days after completion; the task itself stays readable without `output`. A task of another
account answers `404 task_not_found`.

**Scope:** `video:read`.




## OpenAPI

````yaml /api-reference/openapi.yaml get /v1/tasks/{task_id}
openapi: 3.1.0
info:
  title: Five API
  version: 1.0.0
  summary: Generate AI videos from text, images, reference assets and clips.
  description: >
    The Five API turns a text prompt, an image, a set of reference assets or a
    video clip into a short video.


    Every generation is an asynchronous **task**: `POST
    /v1/{brand}/{version}/{task}` returns a `queued` task at

    once, and the result arrives by webhook or by polling `GET
    /v1/tasks/{task_id}`.


    * Base URL: `https://api.fiveapi.ai`

    * Authentication: `Authorization: Bearer <API key>` (or the `x-api-key`
    header)

    * JSON in and out, `snake_case` fields, UTF-8, ISO 8601 UTC timestamps

    * Every response carries `X-Request-Id`; error bodies repeat it as
    `error.request_id`
  contact:
    name: Five API support
    email: support@fiveapi.ai
    url: https://docs.fiveapi.ai
servers:
  - url: https://api.fiveapi.ai
    description: Production
security:
  - bearerAuth: []
tags:
  - name: Video Fast 1.0
    description: Fast, low-cost generation at 480p or 768p.
  - name: Wan 3.0 Spark
    description: Native 30-second video with richer detail and synchronized audio.
  - name: Wan 3.0 Prime Spark
    description: Wan 3.0 quality at full 30 seconds, noticeably faster.
  - name: Video Fast Extend 1.1
    description: Continue an existing clip with matched audio.
  - name: Tasks
    description: Read, list and cancel generation tasks.
  - name: Models
    description: The model catalogue and each model's input schema.
  - name: Account
    description: Balance, plan limits and daily usage.
paths:
  /v1/tasks/{task_id}:
    get:
      tags:
        - Tasks
      summary: Get a task
      description: >
        Returns the current state of a task. While the task is `queued`,
        `queue.position` shows its place in the

        model's queue; once it is `completed`, `output.video.url` holds the MP4.


        Poll every few seconds with backoff, or use
        [webhooks](/concepts/webhooks) instead. The output is removed at

        `expires_at`, 7 days after completion; the task itself stays readable
        without `output`. A task of another

        account answers `404 task_not_found`.


        **Scope:** `video:read`.
      operationId: getTask
      parameters:
        - $ref: '#/components/parameters/TaskId'
      responses:
        '200':
          description: The task.
          headers:
            X-Request-Id:
              $ref: '#/components/headers/X-Request-Id'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Task'
              examples:
                completed:
                  $ref: '#/components/examples/CompletedTask'
                queued:
                  $ref: '#/components/examples/QueuedTask'
                processing:
                  $ref: '#/components/examples/ProcessingTask'
                failed:
                  $ref: '#/components/examples/FailedTask'
                cancelled:
                  $ref: '#/components/examples/CancelledTask'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
        '429':
          $ref: '#/components/responses/TooManyRequests'
components:
  parameters:
    TaskId:
      name: task_id
      in: path
      required: true
      description: The task id (`task_` followed by 26 characters).
      schema:
        type: string
        examples:
          - task_01J9X7Z0K7Q8W3F2P1N6M5V4R3
  headers:
    X-Request-Id:
      description: Id of this request (`req_...`). Quote it when you contact support.
      schema:
        type: string
        examples:
          - req_01M5KPY92Y148QP01G532MM3BH
    Retry-After:
      description: Seconds to wait before retrying.
      schema:
        type: integer
        examples:
          - 10
    X-RateLimit-Limit:
      description: >-
        Requests per minute allowed for your account (or the key's lower
        ceiling).
      schema:
        type: integer
        examples:
          - 300
    X-RateLimit-Remaining:
      description: Requests left in the current minute.
      schema:
        type: integer
        examples:
          - 287
    X-RateLimit-Reset:
      description: Unix time in seconds when the minute window resets.
      schema:
        type: integer
        format: int64
        examples:
          - 1792736640
  schemas:
    Task:
      type: object
      description: >-
        A generation task. `error` is always present (`null` unless the task
        failed); other empty members are omitted.
      required:
        - id
        - object
        - model
        - task
        - status
        - input
        - error
        - credits
        - created_at
      properties:
        id:
          type: string
          description: Task id, `task_` followed by 26 characters.
          examples:
            - task_01J9X7Z0K7Q8W3F2P1N6M5V4R3
        object:
          type: string
          const: task
        model:
          type: string
          description: The model id the task was created with.
          examples:
            - wan/v3.0-spark/image-to-video
        task:
          type: string
          enum:
            - text-to-video
            - image-to-video
            - reference-to-video
            - video-extend
          description: The task type, the last segment of the model id.
        status:
          $ref: '#/components/schemas/TaskStatus'
        input:
          type: object
          additionalProperties: true
          description: The accepted request body, without `webhook_url` and `metadata`.
        output:
          $ref: '#/components/schemas/TaskOutput'
        error:
          description: Why the task failed. `null` unless `status` is `failed`.
          oneOf:
            - $ref: '#/components/schemas/TaskError'
            - type: 'null'
        credits:
          $ref: '#/components/schemas/Credits'
        queue:
          $ref: '#/components/schemas/Queue'
        webhook_url:
          type: string
          format: uri
          description: The webhook URL sent with the task.
        metadata:
          type: object
          additionalProperties: true
          description: The metadata sent with the task.
        created_at:
          type: string
          format: date-time
          description: When the task was created.
        started_at:
          type: string
          format: date-time
          description: When generation started.
        completed_at:
          type: string
          format: date-time
          description: When the task reached `completed`, `failed` or `cancelled`.
        expires_at:
          type: string
          format: date-time
          description: When the output is removed, 7 days after completion.
    TaskStatus:
      type: string
      enum:
        - queued
        - processing
        - completed
        - failed
        - cancelled
      description: >-
        `queued` → `processing` → one of the terminal states `completed`,
        `failed`, `cancelled`.
    TaskOutput:
      type: object
      description: The result. Present on `completed` tasks until `expires_at`.
      properties:
        video:
          $ref: '#/components/schemas/Video'
        actual_prompt:
          type: string
          description: The prompt after expansion, when it was rewritten.
        seed:
          type: integer
          format: int64
          description: The seed used, when the model reports it.
    TaskError:
      type: object
      description: Why a task failed.
      required:
        - code
        - message
        - retryable
      properties:
        code:
          type: string
          enum:
            - input_fetch_failed
            - input_invalid
            - content_moderation_rejected
            - generation_failed
            - timeout
            - service_unavailable
          description: Stable failure code. See [Errors](/concepts/errors#task-failures).
        message:
          type: string
          description: Human-readable detail. It may change; branch on `code`.
        retryable:
          type: boolean
          description: True when submitting the same request again may succeed.
        reason:
          type: string
          enum:
            - ip
            - audio_copyright
            - public_figure
          description: 'For `content_moderation_rejected`: the category, when classified.'
    Credits:
      type: object
      required:
        - estimated
      properties:
        estimated:
          type: integer
          format: int64
          description: Credits held when the task was accepted.
          examples:
            - 60
        charged:
          type: integer
          format: int64
          description: >-
            Credits charged. Set when the task completes; absent on failed and
            cancelled tasks, whose hold was released.
          examples:
            - 60
    Queue:
      type: object
      description: Present while the task is `queued`.
      properties:
        position:
          type: integer
          description: Position in the model's queue; lower starts sooner.
          examples:
            - 3
    Error:
      type: object
      required:
        - error
      properties:
        error:
          type: object
          required:
            - type
            - code
            - message
            - request_id
          properties:
            type:
              type: string
              enum:
                - invalid_request_error
                - authentication_error
                - billing_error
                - permission_error
                - not_found_error
                - conflict_error
                - rate_limit_error
                - api_error
              description: The error category.
            code:
              type: string
              description: >-
                Stable machine-readable code. Branch on this, never on
                `message`.
              examples:
                - insufficient_credits
            message:
              type: string
              description: Human-readable detail. It may change.
            param:
              type: string
              description: The request field at fault, when there is one.
            request_id:
              type: string
              description: Same as the `X-Request-Id` header.
            details:
              type: object
              additionalProperties: true
              description: >-
                Extra members for some codes, for example `required` and
                `available` on `insufficient_credits`.
    Video:
      type: object
      properties:
        url:
          type: string
          format: uri
          description: Download URL of the MP4, valid until `expires_at`.
          examples:
            - >-
              https://openassets.fiveapi.ai/x2v/results/551fe9fa/openapi_1793171336.mp4
        content_type:
          type: string
          examples:
            - video/mp4
        file_size:
          type: integer
          format: int64
          description: Size in bytes.
        width:
          type: integer
          description: Width in pixels.
        height:
          type: integer
          description: Height in pixels.
        duration:
          type: number
          description: Length in seconds.
        fps:
          type: integer
          description: Frames per second.
        cover_url:
          type: string
          format: uri
          description: First-frame image (JPG), when available.
  examples:
    CompletedTask:
      summary: Completed
      value:
        id: task_01J9X7Z0K7Q8W3F2P1N6M5V4R3
        object: task
        model: wan/v3.0-spark/image-to-video
        task: image-to-video
        status: completed
        input:
          image_url: https://assets.example.com/inputs/portrait.jpg
          prompt: slow push-in, soft morning light, hair moving in the breeze
          duration: 5
          resolution: 720p
          aspect_ratio: adaptive
        output:
          video:
            url: >-
              https://openassets.fiveapi.ai/x2v/results/551fe9fa/openapi_1793171336.mp4
            content_type: video/mp4
            file_size: 4823119
            width: 720
            height: 1280
            duration: 5.04
            fps: 24
            cover_url: >-
              https://openassets.fiveapi.ai/x2v/results/61f69823/openapi_1793171336.jpg
          actual_prompt: >-
            A slow cinematic push-in on a young woman in soft morning light, her
            hair moving gently in the breeze.
        error: null
        credits:
          estimated: 60
          charged: 60
        webhook_url: https://hooks.example.com/fiveapi
        metadata:
          order_id: ord_8812
        created_at: '2026-10-23T06:21:02.127Z'
        started_at: '2026-10-23T06:21:40.512Z'
        completed_at: '2026-10-23T06:23:05.004Z'
        expires_at: '2026-10-30T06:23:05.004Z'
    QueuedTask:
      summary: Queued
      value:
        id: task_01J9X7Z0K7Q8W3F2P1N6M5V4R3
        object: task
        model: wan/v3.0-spark/image-to-video
        task: image-to-video
        status: queued
        input:
          image_url: https://assets.example.com/inputs/portrait.jpg
          prompt: slow push-in, soft morning light, hair moving in the breeze
          duration: 5
          resolution: 720p
          aspect_ratio: adaptive
        error: null
        credits:
          estimated: 60
        queue:
          position: 3
        webhook_url: https://hooks.example.com/fiveapi
        metadata:
          order_id: ord_8812
        created_at: '2026-10-23T06:21:02.127Z'
    ProcessingTask:
      summary: Processing
      value:
        id: task_01J9X7Z0K7Q8W3F2P1N6M5V4R3
        object: task
        model: wan/v3.0-spark/image-to-video
        task: image-to-video
        status: processing
        input:
          image_url: https://assets.example.com/inputs/portrait.jpg
          prompt: slow push-in, soft morning light, hair moving in the breeze
          duration: 5
          resolution: 720p
          aspect_ratio: adaptive
        error: null
        credits:
          estimated: 60
        webhook_url: https://hooks.example.com/fiveapi
        metadata:
          order_id: ord_8812
        created_at: '2026-10-23T06:21:02.127Z'
        started_at: '2026-10-23T06:21:40.512Z'
    FailedTask:
      summary: Failed
      value:
        id: task_01J9X8A1B2C3D4E5F6G7H8J9K0
        object: task
        model: video-fast/v1.0/text-to-video
        task: text-to-video
        status: failed
        input:
          prompt: a red kite rising over a windy beach at sunset
          duration: 5
          resolution: 480p
        error:
          code: generation_failed
          message: the model failed to produce a result
          retryable: true
        credits:
          estimated: 9
        created_at: '2026-10-23T06:25:11.000Z'
        started_at: '2026-10-23T06:25:12.200Z'
        completed_at: '2026-10-23T06:25:14.318Z'
    CancelledTask:
      summary: Cancelled
      value:
        id: task_01J9X9C2D3E4F5G6H7J8K9L0M1
        object: task
        model: wan/v3.0-prime-spark/text-to-video
        task: text-to-video
        status: cancelled
        input:
          prompt: macro shot of rain drops hitting a leaf, slow motion
          duration: 4
          resolution: 720p
          aspect_ratio: '9:16'
        error: null
        credits:
          estimated: 64
        created_at: '2026-10-23T06:30:00.000Z'
        completed_at: '2026-10-23T06:30:21.450Z'
  responses:
    Unauthorized:
      description: >-
        The API key is missing, unknown, revoked or expired (`invalid_api_key`,
        `api_key_revoked`, `api_key_expired`).
      headers:
        X-Request-Id:
          $ref: '#/components/headers/X-Request-Id'
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          examples:
            invalid_api_key:
              summary: No key, or an unknown key
              value:
                error:
                  type: authentication_error
                  code: invalid_api_key
                  message: >-
                    missing API key: send Authorization: Bearer sk_live_… (or
                    x-api-key)
                  request_id: req_01M5KN14MXD6SJ01ZQ2FPS6Y8X
            api_key_revoked:
              summary: The key was revoked in the console
              value:
                error:
                  type: authentication_error
                  code: api_key_revoked
                  message: this API key has been revoked
                  request_id: req_01M5KN14PY5YH5QPA2QS7Y07Y4
    Forbidden:
      description: >
        The key lacks the scope (`insufficient_scope`), the caller's IP address
        is not on the key's allowlist

        (`ip_not_allowed`), or the account is suspended or not approved yet
        (`account_suspended`,

        `account_not_active`).
      headers:
        X-Request-Id:
          $ref: '#/components/headers/X-Request-Id'
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          examples:
            insufficient_scope:
              summary: The key lacks the scope
              value:
                error:
                  type: permission_error
                  code: insufficient_scope
                  message: this key does not have the video:write scope
                  request_id: req_01M5KN14S3T4U5V6W7X8Y9Z0A1
            ip_not_allowed:
              summary: The caller is not on the key's IP allowlist
              value:
                error:
                  type: permission_error
                  code: ip_not_allowed
                  message: requests from 203.0.113.9 are not allowed for this key
                  request_id: req_01M5KN14T4U5V6W7X8Y9Z0A1B2
            account_not_active:
              summary: The account is waiting for approval
              value:
                error:
                  type: permission_error
                  code: account_not_active
                  message: this account is not active yet (pending approval)
                  request_id: req_01M5KN14U5V6W7X8Y9Z0A1B2C3
    NotFound:
      description: >-
        Unknown model or task (`model_not_found`, `task_not_found`). A task of
        another account is also a `404`.
      headers:
        X-Request-Id:
          $ref: '#/components/headers/X-Request-Id'
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          examples:
            task_not_found:
              summary: Unknown task
              value:
                error:
                  type: not_found_error
                  code: task_not_found
                  message: 'no such task: task_01ZZZZZZZZZZZZZZZZZZZZZZZZ'
                  request_id: req_01M5KN36WF28NP71BQ6AJ47Q8Y
            model_not_found:
              summary: Unknown model
              value:
                error:
                  type: not_found_error
                  code: model_not_found
                  message: 'no such model: nobrand/v9/text-to-video'
                  param: model
                  request_id: req_01M5KN36QQXYGKNTNVM7WGQPD0
    TooManyRequests:
      description: >
        A limit of your plan was reached: the request rate
        (`rate_limit_exceeded`), the number of queued and

        processing tasks (`concurrency_limit_exceeded`) or the daily credit cap
        (`daily_cap_exceeded`). Wait

        `Retry-After` seconds before retrying.
      headers:
        Retry-After:
          $ref: '#/components/headers/Retry-After'
        X-RateLimit-Limit:
          $ref: '#/components/headers/X-RateLimit-Limit'
        X-RateLimit-Remaining:
          $ref: '#/components/headers/X-RateLimit-Remaining'
        X-RateLimit-Reset:
          $ref: '#/components/headers/X-RateLimit-Reset'
        X-Request-Id:
          $ref: '#/components/headers/X-Request-Id'
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          examples:
            rate_limit_exceeded:
              summary: Too many requests
              value:
                error:
                  type: rate_limit_error
                  code: rate_limit_exceeded
                  message: rate limit exceeded for this account (10 rps, 300 rpm)
                  request_id: req_01M5KN37C3D4E5F6G7H8J9K0L1
            concurrency_limit_exceeded:
              summary: Too many tasks in flight
              value:
                error:
                  type: rate_limit_error
                  code: concurrency_limit_exceeded
                  message: >-
                    the account already has 20 tasks queued or processing (plan
                    limit 20)
                  request_id: req_01M5KN37D4E5F6G7H8J9K0L1M2
            daily_cap_exceeded:
              summary: Daily credit cap reached
              value:
                error:
                  type: rate_limit_error
                  code: daily_cap_exceeded
                  message: this account's daily credit cap (5000) would be exceeded
                  request_id: req_01M5KN37E5F6G7H8J9K0L1M2N3
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: >
        Your API key from the [developer console](https://fiveapi.ai), sent as
        `Authorization: Bearer sk_live_...`.

        The `x-api-key: sk_live_...` header is accepted as an alternative.

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.