> ## Documentation Index > Fetch the complete documentation index at: https://docs.sailresearch.com/llms.txt > Use this file to discover all available pages before exploring further. # Get batch status and results > Poll for batch progress and read inline results once all requests have finished. See [Reading the batch response](/requests_at_scale#reading-the-batch-response) for result handling and [Large batches and individual results](/requests_at_scale#large-batches-and-individual-results) for limits and retries. ## OpenAPI ````yaml /openapi.json get /batches/{batch_id} openapi: 3.1.0 info: title: Sail API version: '2026-02-18' description: >- Sail provides OpenAI-compatible Responses and Chat Completions endpoints, plus an Anthropic-compatible Messages endpoint. This reference documents the currently supported subset of fields. servers: - url: https://api.sailresearch.com/v1 security: - BearerAuth: [] tags: - name: Models API description: Model discovery endpoints. - name: Responses API description: OpenAI-compatible Responses API endpoints. - name: Chat Completions API description: OpenAI-compatible Chat Completions API endpoints. - name: Messages API description: Anthropic-compatible Messages API endpoints. - name: Batches API description: Submit and manage batches of requests. paths: /batches/{batch_id}: get: tags: - Batches API summary: Get batch status and results description: >- Poll for batch progress and read inline results once all requests have finished. See [Reading the batch response](/requests_at_scale#reading-the-batch-response) for result handling and [Large batches and individual results](/requests_at_scale#large-batches-and-individual-results) for limits and retries. operationId: getBatch parameters: - name: batch_id in: path required: true schema: type: string responses: '200': description: >- Batch status and counts, with inline results when complete and within the inline size limit. content: application/json: schema: type: object required: - id - object - endpoint - status - request_counts - created_at - request_status - results - error properties: id: type: string description: Unique identifier for the batch. object: type: string enum: - batch endpoint: type: string enum: - /v1/responses description: Endpoint used by the requests in this batch. status: type: string enum: - in_progress - completed description: >- Completed means every request has finished, including any that failed or were cancelled. request_counts: type: object required: - total - completed - failed description: >- Progress counts for this batch. The create and list endpoints return request_counts as an integer instead. properties: total: type: integer minimum: 0 description: Total number of requests submitted. completed: type: integer minimum: 0 description: >- Requests that finished with a response, including responses with status incomplete. failed: type: integer minimum: 0 description: Requests that failed or were cancelled. created_at: type: integer description: Unix timestamp of when the batch was created. label: type: string description: The label for the batch, if provided. request_status: type: object description: >- Current statuses keyed by custom_id. Status updates may be partial; use the batch status field to decide when it is complete. additionalProperties: type: object required: - status properties: status: type: string enum: - QUEUED - RUNNING - COMPLETED - FAILED - CANCELLED results: description: >- Results for a completed batch, matched to inputs by custom_id. Null while the batch is in progress or when its results exceed the inline size limit. oneOf: - type: array items: type: object required: - id - custom_id - response - error properties: id: type: string description: Response ID for this request. custom_id: type: string description: The custom_id supplied on submission. response: description: >- The response for a completed request; null for a failed or cancelled request. oneOf: - type: object required: - status_code - request_id - body properties: status_code: type: integer enum: - 200 request_id: type: string description: Response ID for this request. body: $ref: '#/components/schemas/ResponseObject' - type: 'null' error: description: >- Error details for a failed or cancelled request; null when response is present. oneOf: - type: object additionalProperties: true - type: 'null' - type: 'null' error: description: >- Null unless inline results are unavailable because the batch exceeds the inline size limit. In that case, code is batch_results_too_large; retrieve results by custom_id. oneOf: - type: object required: - code - message properties: code: type: string enum: - batch_results_too_large message: type: string - type: 'null' examples: in_progress: summary: Batch still running value: id: batch_abc123 object: batch endpoint: /v1/responses status: in_progress request_counts: total: 2 completed: 1 failed: 0 created_at: 1741564800 label: my-batch-job request_status: my-first-request: status: COMPLETED my-second-request: status: RUNNING results: null error: null completed: summary: Completed batch with a successful and a failed request value: id: batch_abc123 object: batch endpoint: /v1/responses status: completed request_counts: total: 2 completed: 1 failed: 1 created_at: 1741564800 label: my-batch-job request_status: my-first-request: status: COMPLETED my-second-request: status: FAILED results: - id: resp_abc123 custom_id: my-first-request response: status_code: 200 request_id: resp_abc123 body: id: resp_abc123 object: response created_at: 1741564801 status: completed model: zai-org/GLM-5.3 output: - type: message role: assistant content: - type: output_text text: Hello! metadata: {} usage: null error: null - id: resp_def456 custom_id: my-second-request response: null error: code: server_error message: task failed during processing error: null results_too_large: summary: Completed batch requiring individual retrieval value: id: batch_abc123 object: batch endpoint: /v1/responses status: completed request_counts: total: 2 completed: 1 failed: 1 created_at: 1741564800 label: my-batch-job request_status: my-first-request: status: COMPLETED my-second-request: status: FAILED results: null error: code: batch_results_too_large message: >- estimated inline results exceed 1 GiB; retrieve results through /v1/batches/{batch_id}/{custom_id} '400': description: Invalid request. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Authentication error. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '404': description: Batch not found. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: Server error. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '503': description: Results are temporarily unavailable. Retry the request. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' components: schemas: ResponseObject: type: object required: - id - object - created_at - status - model - metadata - usage properties: id: type: string object: type: string enum: - response created_at: type: integer status: type: string enum: - queued - in_progress - failed - completed - incomplete - cancelled model: type: string input: $ref: '#/components/schemas/ResponseInput' output: oneOf: - type: string - type: array items: type: object additionalProperties: true - type: object additionalProperties: true - type: 'null' error: oneOf: - type: object additionalProperties: true - type: 'null' incomplete_details: oneOf: - type: object additionalProperties: true - type: 'null' max_output_tokens: oneOf: - type: integer - type: 'null' reasoning: type: object additionalProperties: true text: $ref: '#/components/schemas/ResponseTextConfiguration' store: type: boolean temperature: type: number top_p: type: number parallel_tool_calls: type: boolean tool_choice: oneOf: - type: string - type: object additionalProperties: true tools: type: array items: type: object additionalProperties: true truncation: oneOf: - type: string - type: object additionalProperties: true usage: oneOf: - $ref: '#/components/schemas/ResponseUsage' - type: 'null' user: oneOf: - type: string - type: 'null' metadata: type: object description: >- Response metadata. A completed response includes supercached_input_tokens and supercache_write_input_tokens as decimal strings when Supercache accounting data is available. Both fields are included when their value is zero. properties: supercached_input_tokens: type: string pattern: ^[0-9]+$ description: Input tokens served from Supercache. supercache_write_input_tokens: type: string pattern: ^[0-9]+$ description: Input tokens written to Supercache for later requests. additionalProperties: true additionalProperties: true ErrorResponse: type: object required: - error properties: error: $ref: '#/components/schemas/ErrorObject' additionalProperties: false ResponseInput: description: >- Text input, plus image input (input_image) on multimodal models and inline PDF input (input_file) on every model. Audio, files referenced by file_id or file_url, and item references are not currently supported. oneOf: - type: string minLength: 1 - type: array minItems: 1 items: $ref: '#/components/schemas/ResponseInputMessage' - $ref: '#/components/schemas/ResponseInputObject' ResponseTextConfiguration: type: object required: - format properties: format: oneOf: - $ref: '#/components/schemas/ResponseTextFormat' - $ref: '#/components/schemas/ResponseJsonSchemaFormat' additionalProperties: false ResponseUsage: type: object required: - input_tokens - input_tokens_details - output_tokens - output_tokens_details - total_tokens properties: input_tokens: type: integer input_tokens_details: $ref: '#/components/schemas/ResponseUsageDetails' output_tokens: type: integer output_tokens_details: $ref: '#/components/schemas/ResponseUsageDetails' total_tokens: type: integer prompt_tokens: type: integer completion_tokens: type: integer additionalProperties: false ErrorObject: type: object required: - message - type properties: message: type: string type: type: string param: oneOf: - type: string - type: 'null' code: oneOf: - type: string - type: integer - type: 'null' additionalProperties: true ResponseInputMessage: type: object required: - role - content properties: role: type: string enum: - system - user - assistant - tool - function content: oneOf: - type: string - type: array minItems: 1 items: oneOf: - $ref: '#/components/schemas/ResponseInputTextPart' - $ref: '#/components/schemas/ResponseInputImagePart' - $ref: '#/components/schemas/ResponseInputFilePart' name: type: string tool_calls: type: array items: type: object additionalProperties: true tool_call_id: type: string function_call: type: object additionalProperties: true additionalProperties: false ResponseInputObject: type: object required: - messages properties: messages: type: array minItems: 1 items: $ref: '#/components/schemas/ResponseInputMessage' additionalProperties: false ResponseTextFormat: type: object required: - type properties: type: type: string enum: - text additionalProperties: false ResponseJsonSchemaFormat: type: object required: - type - name properties: type: type: string enum: - json_schema name: type: string description: type: string schema: type: object additionalProperties: true strict: type: boolean additionalProperties: false ResponseUsageDetails: type: object required: - cached_tokens - reasoning_tokens properties: cached_tokens: type: integer description: >- Input tokens served from regular cache or Supercache. This is an aggregate count. reasoning_tokens: type: integer additionalProperties: false ResponseInputTextPart: type: object required: - type - text properties: type: type: string enum: - input_text text: type: string additionalProperties: false ResponseInputImagePart: type: object description: >- Image content part. Image input is supported only on multimodal models; see the Models page. required: - type - image_url properties: type: type: string enum: - input_image image_url: type: string description: >- Public http(s) URL or a base64 data URI (data:;base64,). detail: type: string enum: - auto - low - high additionalProperties: false ResponseInputFilePart: type: object description: >- PDF file content part. Sail sends the PDF's text to the model, so this works on every model. See [PDF input](/support#pdf-input). required: - type - file_data properties: type: type: string enum: - input_file file_data: type: string description: >- The PDF as a base64 data URI (data:application/pdf;base64,), or raw base64 when filename ends in .pdf. filename: type: string description: Name used to label the PDF's text. additionalProperties: false securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: API Key ````