Skip to content
OpenRelay is in early access, and the /v1 API is stable. New capabilities ship in the changelog.
PricingDashboard
GuidesAPI ReferenceCLI
API ReferenceInferenceFiles

Download a file's raw JSONL content

Streams a file's raw bytes as application/octet-stream, for a batch input file you uploaded or a result file that a batch has written. Use it to fetch batch results: the batch object's output_file_id (successful records) and error_file_id (failed records) each point at a JSONL file of `{custom_id, response | error}` lines.

Required permission

Requires the batch.read permission. See Permissions for the roles and API key permissions that include it.

Command line

The orl CLI wraps this endpoint:

orl files content get <id>
GET
/v1/files/{id}/content

Authorization

apiKey
headerAuthorizationBearer <token>

OpenRelay API key. Send it as Authorization: Bearer or_… (legacy vl_… keys still work).

Path Parameters

id*string

Response Body

The file's raw JSONL bytes

response?fileapplication/octet-stream
Formatbinary
Example Request
curl -X GET 'https://inference.openrelay.inc/v1/files/string/content'
Example Response
"string"

Get a file's metadata GET

Returns a file's metadata (id, size in bytes, purpose, and creation and expiry times) for a batch input or result file, without its content. The filename is assigned by the server, not the name you uploaded.

Overview

Models served on capacity reserved for your organization. Call one through the inference API at inference.openrelay.inc with its modelId. Read it, its lifecycle events, and its monitoring series here. Dedicated endpoints are set up with our team; without dedicated inference the list is empty and the rest return 404.