Run batch inference with Portkey
Provider | Supported Endpoints |
---|---|
OpenAI | completions , chat completions , embedding |
Bedrock | chat completions |
Azure OpenAI | completions , chat completions , embedding |
Vertex | embedding , chat completions |
completion_window
parameter in the request.
completion_window
is set to 24h
, Portkey will batch requests with Provider’s batch API using Portkey’s file.completion_window
is set to immediate
, Portkey will batch requests directly with Portkey’s gateway.portkey_options
which helps Portkey to batch requests to Provider’s batch API or Gateway.
portkey_options
to {"x-portkey-virtual-key": "openai-virtual_key"}
completion_window
needs to be set to 24h
and input_file_id
needs to be Portkey’s file id. Please refer to Portkey’s files for more details.GET /batches/<batch_id>/output
endpoint.completion_window
needs to be set to immediate
and input_file_id
needs to be Portkey’s file id. Please refer to Portkey’s files for more details.x-portkey-config
header with retry)