# Sora2 Text to Video ## OpenAPI Specification ```yaml openapi: 3.0.1 info: title: '' description: '' version: 1.0.0 paths: /api/v1/task: post: summary: Sora2 Text to Video deprecated: false description: >- **⚠️ Deprecation notice — Sora 2 will be discontinued on September 24, 2026.** OpenAI is removing the Sora 2 models and its Videos API on that date and has not announced a replacement, so this endpoint will stop working then. For alternatives, see our Veo 3.1, Kling and Wan 2.6 video endpoints. This is provided as Sora2 Text to Video API. available models: - sora2-video Pricing | Model | Price | | --- | --- | | sora2-video | $0.08/s | Note - be aware of the endpoint api/v1/task - only 720p is available currently operationId: sora2/text-to-video tags: - Endpoints/Sora2 parameters: - name: X-API-Key in: header description: Your API KEY used for request authorization required: true example: '' schema: type: string requestBody: content: application/json: schema: type: object properties: model: type: string description: the model name, should be 'sora2' enum: - sora2 x-apidog-enum: - value: sora2 name: '' description: '' task_type: type: string description: the task_type enum: - sora2-video x-apidog-enum: - value: sora2-video name: '' description: '' input: type: object properties: prompt: type: string description: The text prompt describing the video to generate image_url: type: string description: The url of image used as first frame of generated video aspect_ratio: type: string description: The aspect ratio of the generated video enum: - '16:9' - '9:16' x-apidog-enum: - value: '16:9' name: '' description: '' - value: '9:16' name: '' description: '' default: '16:9' duration: type: integer description: The duration of the generated video in seconds enum: - 4 - 8 - 12 x-apidog-enum: - value: 4 name: '' description: '' - value: 8 name: '' description: '' - value: 12 name: '' description: '' default: 4 resolution: type: string description: The resolution of the generated video enum: - 720p x-apidog-enum: - value: 720p name: '' description: '' default: 720p x-apidog-orders: - prompt - image_url - aspect_ratio - duration - resolution required: - prompt description: | the input param of the flux task x-apidog-ignore-properties: [] config: type: object properties: webhook_config: type: object properties: endpoint: type: string secret: type: string description: >- Webhook provides timely task notifications. Check [PiAPI webhook](/docs/unified-webhook) for detail. x-apidog-orders: - endpoint - secret x-apidog-ignore-properties: [] service_mode: type: string description: > This allows users to choose whether this specific task will get processed under PAYG or HYA mode. If unspecified, then this task will get processed under whatever mode (PAYG or HYA) the user chose on the workspace setting of your account. - `public` means this task will be processed under PAYG mode. - `private` means this task will be processed under HYA mode. enum: - public - private x-apidog-orders: - webhook_config - service_mode x-apidog-ignore-properties: [] x-apidog-refs: 01J8PNX50491VGB1V6ZTHX081W: $ref: '#/components/schemas/config' x-apidog-orders: - model - task_type - input - 01J8PNX50491VGB1V6ZTHX081W required: - model - task_type - input x-apidog-ignore-properties: - config example: model: sora2 task_type: sora2-video input: prompt: >- A casual street interview on a busy New York City sidewalk in the afternoon. The interviewer holds a plain, unbranded microphone and asks: Have you seen OpenAI's new Sora2 model It is a super good model. Person replies: Yeah I saw it, it's already available on PiAPI. It's crazy good. aspect_ratio: '16:9' duration: 4 config: webhook_config: endpoint: https://webhook.site/74ff2ef5-7120-493c-a0ff-123e2554e754 secret: '' responses: '200': description: '' content: application/json: schema: type: object properties: code: type: integer data: type: object properties: task_id: type: string model: type: string task_type: type: string status: type: string enum: - Completed - Processing - Pending - Failed - Staged x-apidog-enum: - value: Completed name: '' description: '' - value: Processing name: '' description: >- Means that your jobs is currently being processed. Number of "processing" jobs counts as part of the "concurrent jobs" - value: Pending name: '' description: >- Means that we recognizes the jobs you sent should be processed by MJ/Luma/Suno/Kling/etc but right now none of the account is available to receive further jobs. During peak loads there can be longer wait time to get your jobs from "pending" to "processing". If reducing waiting time is your primary concern, then a combination of Pay-as-you-go and Host-your-own-account option might suit you better.Number of "pending" jobs counts as part of the "concurrent jobs" - value: Failed name: '' description: Task failed. Check the error message for detail. - value: Staged name: '' description: >- A stage only in Midjourney task . Means that you have exceeded the number of your "concurrent jobs" limit and your jobs are being queuedNumber of "staged" jobs does not count as part of the "concurrent jobs". Also, please note the maximum number of jobs in the "staged" queue is 50. So if your operational needs exceed the 50 jobs limit, then please create your own queuing system logic. description: >- Hover on the "Completed" option and you coult see the explaintion of all status: completed/processing/pending/failed/staged input: type: object properties: {} x-apidog-orders: [] x-apidog-ignore-properties: [] output: type: object properties: image_url: type: string description: if the result contains only one image image_urls: type: array items: type: string description: if the result contains multiple images x-apidog-orders: - image_url - image_urls x-apidog-ignore-properties: [] meta: type: object properties: created_at: type: string description: >- The time when the task was submitted to us (staged and/or pending) started_at: type: string description: >- The time when the task started processing. the time from created_at to time of started_at is time the job spent in the "staged“ stage and/or the"pending" stage if there were any. ended_at: type: string description: The time when the task finished processing. usage: type: object properties: type: type: string frozen: type: number consume: type: number x-apidog-orders: - type - frozen - consume required: - type - frozen - consume x-apidog-ignore-properties: [] is_using_private_pool: type: boolean x-apidog-orders: - created_at - started_at - ended_at - usage - is_using_private_pool required: - usage - is_using_private_pool x-apidog-ignore-properties: [] detail: type: 'null' logs: type: array items: type: object properties: {} x-apidog-orders: [] x-apidog-ignore-properties: [] error: type: object properties: code: type: integer message: type: string x-apidog-orders: - code - message x-apidog-ignore-properties: [] x-apidog-orders: - task_id - model - task_type - status - input - output - meta - detail - logs - error required: - task_id - model - task_type - status - input - output - meta - detail - logs - error x-apidog-ignore-properties: [] message: type: string description: >- If you get non-null error message, here are some steps you chould follow: - Check our [common error message](https://climbing-adapter-afb.notion.site/Common-Error-Messages-6d108f5a8f644238b05ca50d47bbb0f4) - Retry for several times - If you have retried for more than 3 times and still not work, file a ticket on Discord and our support will be with you soon. x-apidog-refs: {} x-apidog-orders: - code - data - message required: - code - data - message x-apidog-ignore-properties: [] example: code: 200 data: task_id: 4eba5893-2a39-4218-b5aa-bb9f3c4a26b2 model: sora2 task_type: sora2-video status: pending config: service_mode: '' webhook_config: endpoint: >- https://webhook.site/74ff2ef5-7120-493c-a0ff-123e2554e754 secret: '' input: prompt: >- A casual street interview on a busy New York City sidewalk in the afternoon. The interviewer holds a plain, unbranded microphone and asks: Have you seen OpenAI's new Sora2 model It is a super good model. Person replies: Yeah I saw it, it's already available on PiAPI. It's crazy good. aspect_ratio: '16:9' duration: 4 output: null meta: created_at: '2025-10-29T02:33:03.28237536Z' started_at: '0001-01-01T00:00:00Z' ended_at: '0001-01-01T00:00:00Z' usage: type: llm frozen: 0 consume: 3200000 is_using_private_pool: false detail: null logs: [] error: code: 0 raw_message: '' message: '' detail: null message: success headers: {} x-apidog-name: Success security: [] x-apidog-folder: Endpoints/Sora2 x-apidog-status: released x-run-in-apidog: https://app.apidog.com/web/project/675356/apis/api-23467938-run components: schemas: config: type: object properties: config: type: object properties: webhook_config: type: object properties: endpoint: type: string secret: type: string description: >- Webhook provides timely task notifications. Check [PiAPI webhook](/docs/unified-webhook) for detail. x-apidog-orders: - endpoint - secret x-apidog-ignore-properties: [] service_mode: type: string description: > This allows users to choose whether this specific task will get processed under PAYG or HYA mode. If unspecified, then this task will get processed under whatever mode (PAYG or HYA) the user chose on the workspace setting of your account. - `public` means this task will be processed under PAYG mode. - `private` means this task will be processed under HYA mode. enum: - public - private x-apidog-orders: - webhook_config - service_mode x-apidog-ignore-properties: [] x-apidog-orders: - config x-apidog-ignore-properties: [] x-apidog-folder: '' securitySchemes: {} servers: - url: https://api.piapi.ai description: Develop Env security: [] ```