Submit a batch inference job
Submits a batch of queries for asynchronous processing. Returns immediately with a job ID that can be used to track progress and retrieve results…
POST
Submits a batch of queries for asynchronous processing. Returns immediately
with a job ID that can be used to track progress and retrieve results.
Use Cases
Required scope:
- Processing large datasets that exceed single-request timeouts
- Running inference on multiple queries in parallel
- Background processing without blocking the client Example
write
Request body
BatchInferRequest
boolean
Include explanations
string[]
required
List of input queries
integer
Maximum reasoning depth
Response
JobSubmitResponse
string
required
Job identifier for tracking
JobStatus
required
integer
required
Estimated items to process