orl decisions create
Answer typed questions about an input with a classifier, part of the orl CLI for OpenRelay GPU VMs, pods, batches and billing.
orl decisions create --model <model> --questions <questions> --state <state>Answers typed questions about a text or JSON input with a classifier: a choice, a score or a yes/no, with probabilities. Bills input tokens only. Each answer carries its probabilities and a confidence; nothing is generated. Served by openrelay/laya; check a model's supported_apis on GET /v1/models for decisions. Online only: the Batch API does not accept /v1/decisions.
Requires a funded balance. Any field this schema does not list is rejected with 400 unknown_field. stream is dropped: a decision is always a single JSON response. Limits: 1 to 64 questions per request, 10 MiB request body.
Flags
| Flag | Type | Required | |
|---|---|---|---|
--model | string | yes | openrelay/laya. |
--questions | json | yes | Question id to question ({type, instructions, criteria}). Between 1 and 64 questions. |
--state | json | yes | The input to decide about. Objects and arrays are serialized to JSON text before the model reads them. |
--max-cost | float64 | no | refuse (exit 8) when the worst-case cost exceeds this many dollars (default: ORL_MAX_COST_USD) |
--body | string | no | a JSON object of request body fields, merged under any of this command's own flags that are also set, e.g. {"key":"value"} |
--body-file | string | no | read the --body JSON object from a file (- for stdin) |
This wraps the createDecision API operation.
orl chat-completions create
Generate a chat completion, part of the orl CLI for OpenRelay GPU VMs, pods, batches and billing. Usage, every flag and an example.
orl dedicated-endpoints event list
List a dedicated endpoint's events, part of the orl CLI for OpenRelay GPU VMs, pods, batches and billing. Usage, every flag and an example.