Create Batch
Body
Gateway supported body params for OpenAI, Azure OpenAI and VertexAI.
The input file to use for the batch job
Completion window for the batch job, immediate
is only supported with Portkey Managed Batching.
immediate
, 24h
Inference endpoint
/v1/chat/completions
, /v1/completions
, /v1/embeddings
metadata related for the batch job
Response
The object type, which is always batch
.
batch
The Portkey API endpoint used by the batch.
The ID of the input file for the batch.
The time frame within which the batch should be processed.
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 created.
The ID of the file containing the outputs of successfully executed requests.
The ID of the file containing the outputs of requests with errors.
The Unix timestamp (in seconds) for when the batch started processing.
The Unix timestamp (in seconds) for when the batch will expire.
The Unix timestamp (in seconds) for when the batch started finalizing.
The Unix timestamp (in seconds) for when the batch was completed.
The Unix timestamp (in seconds) for when the batch failed.
The Unix timestamp (in seconds) for when the batch expired.
The Unix timestamp (in seconds) for when the batch started cancelling.
The Unix timestamp (in seconds) for when the batch was cancelled.
The request counts for different statuses within the batch.
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. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.
Was this page helpful?