Create a new batch of API requests.
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.
The time frame within which the batch should be processed. Currently only unlimited is supported.
The endpoint to be used for all requests in the batch. Currently v1/responses, v1/chat/completions, v1/embeddings, and v1/completions are supported. Note that v1/embeddings batches are also restricted to a maximum of 50,000 embedding inputs across all requests in the batch.
The ID of an uploaded file that contains requests for the new batch. See upload file for how to upload a file. Your input file must be formatted as a JSONL file, and must be uploaded with the purpose batch. The file can contain up to 50,000 requests, and can be up to 200 MB in size.
ID of the Job definition this batch belongs to. Links the batch to a specific model, use case, and SLA.
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.
The expiration policy for the output and/or error file that are generated for a batch.
Successful Response
The time frame within which the batch should be processed.
The Unix timestamp (in seconds) for when the batch was created.
The OpenAI API endpoint used by the batch.
The unique identifier for the batch.
ID of the Job definition this batch belongs to.
The ID of the input file for the batch.
The request counts for different statuses within the batch.
The current status of the batch.
validating, failed, in_progress, finalizing, completed, expired, cancelling, cancelled The Unix timestamp (in seconds) for when the batch was cancelled.
The Unix timestamp (in seconds) for when the batch started cancelling.
The Unix timestamp (in seconds) for when the batch was completed.
The ID of the file containing the outputs of requests with errors.
The errors encountered during batch processing.
The Unix timestamp (in seconds) for when the batch expired.
The Unix timestamp (in seconds) for when the batch will expire.
The Unix timestamp (in seconds) for when the batch failed.
The Unix timestamp (in seconds) for when the batch started finalizing.
The Unix timestamp (in seconds) for when the batch started processing.
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.
The object type, which is always batch.
"batch"The ID of the file containing the outputs of successfully executed requests.