> ## Documentation Index > Fetch the complete documentation index at: https://docs.getimpala.ai/llms.txt > Use this file to discover all available pages before exploring further. # Get Batch > Retrieve a specific batch. ## OpenAPI ````yaml /openai-api-swagger.json get /v1/batches/{batch_id} openapi: 3.1.0 info: title: impala.ai OpenAI API v0.1.0 description: >- An OpenAI API compatible server for impala.ai All timestamps are Unix epoch seconds, UTC. A null `*_at` field means the event did not occur for this run. All costs in USD. version: 0.1.0 servers: [] security: [] paths: /v1/batches/{batch_id}: get: tags: - batches summary: Get Batch description: Retrieve a specific batch. operationId: get_batch_v1_batches__batch_id__get parameters: - name: batch_id in: path required: true schema: type: string title: Batch Id responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/BatchModel' '404': content: application/json: schema: $ref: '#/components/schemas/ErrorResponseModel' description: Not Found '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: BatchModel: properties: cancelled_at: anyOf: - type: integer - type: 'null' title: Cancelled At description: The Unix timestamp (in seconds) for when the batch was cancelled. cancelling_at: anyOf: - type: integer - type: 'null' title: Cancelling At description: >- The Unix timestamp (in seconds) for when the batch started cancelling. completed_at: anyOf: - type: integer - type: 'null' title: Completed At description: The Unix timestamp (in seconds) for when the batch was completed. completion_window: type: string title: Completion Window description: The time frame within which the batch should be processed. created_at: type: integer title: Created At description: The Unix timestamp (in seconds) for when the batch was created. endpoint: type: string title: Endpoint description: The OpenAI API endpoint used by the batch. error_file_id: anyOf: - type: string - type: 'null' title: Error File Id description: The ID of the file containing the outputs of requests with errors. errors: anyOf: - $ref: '#/components/schemas/BatchErrorsModel' - type: 'null' description: The errors encountered during batch processing. expired_at: anyOf: - type: integer - type: 'null' title: Expired At description: The Unix timestamp (in seconds) for when the batch expired. expires_at: anyOf: - type: integer - type: 'null' title: Expires At description: The Unix timestamp (in seconds) for when the batch will expire. failed_at: anyOf: - type: integer - type: 'null' title: Failed At description: The Unix timestamp (in seconds) for when the batch failed. finalizing_at: anyOf: - type: integer - type: 'null' title: Finalizing At description: >- The Unix timestamp (in seconds) for when the batch started finalizing. id: type: string title: Id description: The unique identifier for the batch. job_id: type: string title: Job Id description: ID of the Job definition this batch belongs to. in_progress_at: anyOf: - type: integer - type: 'null' title: In Progress At description: >- The Unix timestamp (in seconds) for when the batch started processing. input_file_id: type: string title: Input File Id description: The ID of the input file for the batch. metadata: additionalProperties: type: string type: object title: Metadata description: >- Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. model: type: string title: Model description: The model used for this batch run. default: '' object: type: string const: batch title: Object description: The object type, which is always `batch`. default: batch output_file_id: anyOf: - type: string - type: 'null' title: Output File Id description: >- The ID of the file containing the outputs of successfully executed requests. price_1m_tokens: type: number title: Price 1M Tokens description: Effective price in USD per 1,000,000 tokens. default: 0 request_counts: $ref: '#/components/schemas/RequestCountsModel' description: The request counts for different statuses within the batch. status: $ref: '#/components/schemas/BatchStatus' description: The current status of the batch. processing_cost: type: number title: Processing Cost description: Total processing cost in USD. default: 0 usage: $ref: '#/components/schemas/CompletionUsageModel' description: Usage statistics for the completion request. type: object required: - completion_window - created_at - endpoint - id - job_id - input_file_id - request_counts - status title: BatchModel ErrorResponseModel: properties: error: $ref: '#/components/schemas/ErrorDetail' description: The error details. type: object required: - error title: ErrorResponseModel HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError BatchErrorsModel: properties: data: items: $ref: '#/components/schemas/BatchErrorModel' type: array title: Data description: A list of errors encountered during batch processing. object: type: string const: list title: Object description: The object type, which is always `list`. default: list type: object required: - data title: BatchErrorsModel RequestCountsModel: properties: completed: type: integer title: Completed description: Number of requests that have been completed successfully. failed: type: integer title: Failed description: Number of requests that have failed. total: type: integer title: Total description: Total number of requests in the batch. type: object required: - completed - failed - total title: RequestCountsModel BatchStatus: type: string enum: - validating - failed - in_progress - finalizing - completed - expired - cancelling - cancelled title: BatchStatus CompletionUsageModel: properties: prompt_tokens: type: number title: Prompt Tokens description: Number of tokens in the prompt (total input tokens processed). default: 0 completion_tokens: type: number title: Completion Tokens description: Number of tokens in the generated completion. default: 0 total_tokens: type: number title: Total Tokens description: Total number of tokens used in the request (prompt + completion). default: 0 type: object title: CompletionUsageModel description: Token usage for the batch run (OpenAI / litellm convention). ErrorDetail: properties: message: type: string title: Message description: A human-readable error message. type: type: string title: Type description: The type of error. param: anyOf: - type: string - type: 'null' title: Param description: The parameter that caused the error, if applicable. code: anyOf: - type: string - type: 'null' title: Code description: An error code, if applicable. type: object required: - message - type title: ErrorDetail ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError BatchErrorModel: properties: code: type: string title: Code description: An error code identifying the error type. line: anyOf: - type: integer - type: 'null' title: Line description: >- The line number of the input file where the error occurred, if applicable. message: type: string title: Message description: A human-readable message providing more details about the error. param: anyOf: - type: string - type: 'null' title: Param description: The name of the parameter that caused the error, if applicable. type: object required: - code - line - message - param title: BatchErrorModel ````