> ## Documentation Index > Fetch the complete documentation index at: https://docs.woodwide.ai/llms.txt > Use this file to discover all available pages before exploring further. # Async Infer (Dataset) > Run inference asynchronously using a dataset reference instead of a file upload. Reference input data by `dataset_id` (latest ready version) or `dataset_version_id`. Returns a `job_id` immediately. Poll `GET /jobs/{job_id}` until status is `succeeded`, then fetch results via `GET /jobs/{job_id}/results`. See [Output Formats](/api-reference/inference#output-formats) for output columns by model type. ## OpenAPI ````yaml /openapi.json post /models/{model_id}/infer-batch openapi: 3.1.0 info: title: Woodwide API description: API service for the Woodwide platform version: 0.1.0 servers: - url: https://api.woodwide.ai description: Production security: [] paths: /models/{model_id}/infer-batch: post: tags: - Inference summary: Async Infer (Dataset) description: >- Run inference asynchronously using a dataset reference instead of a file upload. operationId: infer_batch_models__model_id__infer_batch_post parameters: - name: model_id in: path required: true schema: type: string format: uuid title: Model Id requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/InferBatchRequest' example: dataset_id: a1b2c3d4-0000-0000-0000-000000000001 output_type: json responses: '202': description: >- Successful Response Output format depends on the `output_type` parameter (json, csv, or parquet). See [Output Formats](/api-reference/inference#output-formats) for output columns by model type. content: application/json: schema: $ref: '#/components/schemas/InferBatchResponse' example: job_id: c3d4e5f6-0000-0000-0000-000000000004 status: queued model: id: b2c3d4e5-0000-0000-0000-000000000001 version_id: b2c3d4e5-0000-0000-0000-000000000002 version_number: 1 '401': description: Unauthorized -- API key is missing or invalid. content: application/json: schema: type: object properties: detail: type: string example: Not authenticated '403': description: >- Forbidden -- your API key does not have permission for this resource. content: application/json: schema: type: object properties: detail: type: string example: Forbidden '404': description: Not Found -- the requested resource does not exist. content: application/json: schema: type: object properties: detail: type: string example: Not found '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' '429': description: >- Too Many Requests -- you have exceeded the rate limit. Heavy operations (training, inference, dataset uploads) are limited to 60 requests per minute per API key. All other endpoints are limited to 600 requests per minute per API key. content: application/json: schema: type: object properties: detail: type: string example: Rate limit exceeded. Retry after a short delay. security: - HTTPBearer: [] components: schemas: InferBatchRequest: properties: model_version_id: type: string format: uuid title: Model Version Id description: >- Pin a specific model version. If omitted, the latest ready version is used. dataset_version_id: type: string format: uuid title: Dataset Version Id description: Pin a specific dataset version for inference input. dataset_id: type: string format: uuid title: Dataset Id description: >- Dataset to run inference on (uses latest ready version). Provide this OR dataset_version_id. output_type: $ref: '#/components/schemas/OutputType' description: 'Output format: json, csv, or parquet.' default: parquet anomaly_format: $ref: '#/components/schemas/AnomalyFormat' description: >- Controls anomaly detection output shape. 'ids_only' returns a list of anomalous row indices. 'per_row' returns id, is_anomaly, and anomaly_score for every input row. Ignored for non-anomaly model types. default: ids_only type: object title: InferBatchRequest description: |- Request body for asynchronous dataset inference. Reference input data by ``dataset_id`` (resolves to the latest ready version) or ``dataset_version_id`` for reproducibility. Optionally pin a ``model_version_id``. InferBatchResponse: properties: job_id: type: string format: uuid title: Job Id status: type: string title: Status model: $ref: '#/components/schemas/ModelVersionRef' type: object required: - job_id - status - model title: InferBatchResponse description: Async inference submission response. example: job_id: c3d4e5f6-0000-0000-0000-000000000004 status: queued model: id: b2c3d4e5-0000-0000-0000-000000000001 version_id: b2c3d4e5-0000-0000-0000-000000000002 version_number: 1 HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError description: Returned when request parameters or body fail validation. OutputType: type: string enum: - json - csv - parquet title: OutputType description: Supported inference output formats. AnomalyFormat: type: string enum: - ids_only - per_row title: AnomalyFormat description: |- Controls anomaly detection output format. - ``ids_only`` (default): returns a compact list of anomalous row indices. - ``per_row``: returns a row for every input instance with ``is_anomaly`` (bool) and ``anomaly_score`` (float) columns. ModelVersionRef: properties: id: type: string format: uuid title: Id version_id: type: string format: uuid title: Version Id version_number: type: integer title: Version Number type: object required: - id - version_id - version_number title: ModelVersionRef description: Model version reference. ValidationError: type: object required: - loc - msg - type properties: loc: type: array items: type: string title: Location description: Path to the field that caused the error. msg: type: string title: Message description: Human-readable error message. type: type: string title: Error Type description: Machine-readable error type identifier. title: ValidationError securitySchemes: HTTPBearer: type: http scheme: bearer ````