Cost and traffic commands
These commands cover what an organization spends on inference. Every command on this page is a subcommand of akka optimize. See akka optimize for every command and flag. Most commands read the document from standard input when you pass -f -.
Spend
akka optimize spend reports what a period consumed, what it cost, and what one conversation cost. The alias spends is accepted.
| Command | Description |
|---|---|
|
What a period consumed and cost, divided as asked. |
|
Two periods, and the difference between them. |
|
A period divided into UTC hours or days, each answered as a read of that hour or day alone. |
|
The most recent exchanges, newest first. |
|
The conversations of a period that cost the most. |
|
Every system id the service has seen, with how many exchanges named it and the first and the last hour in which one did. |
|
Which service is answering at this address. |
Pricing catalog
akka optimize pricing-catalog holds model prices as input and output rates per million tokens for each served name. A published version is never edited. The aliases pricing-catalogs, catalog, and catalogs are accepted.
| Command | Description |
|---|---|
|
The prices in force now, or at an instant. |
|
Publish a catalog version, or check one. |
|
Every published version, newest first. |
Captures
akka optimize captures reads recorded interaction artifacts off a filesystem. The alias capture is accepted.
These commands serve debugging and diagnostics. They read artifacts from a directory on disk, which is where a capture written during local development or a support investigation lands.
|
Captures recorded in production are stored in a location the CLI cannot reach in this version. The commands below read a filesystem directory only. |
| Command | Description |
|---|---|
|
Every artifact in a directory, newest first. |
|
One artifact, read forward. |
| The features described in this section are an add-on to Akka Automated Operations. They are not included in the base product. |
For pricing rules, unpriced traffic, reporting completeness, and attribution, see Understanding inference costs. For how the gateway records traffic, see Capture and grading.