Get aggregated usage

GET

/api/v1/chat/usage

const url = 'http://localhost:11044/api/v1/chat/usage';
const options = {method: 'GET', headers: {'X-Embabel-Api-Key': '<X-Embabel-Api-Key>'}};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}

curl --request GET \
  --url http://localhost:11044/api/v1/chat/usage \
  --header 'X-Embabel-Api-Key: <X-Embabel-Api-Key>'

Returns aggregated LLM token usage, cost, and models used across the chat session and all child processes (action invocations, sidecars, cron, webhooks). This gives the true total cost of the session, not just the main chat process. A session with no process yet returns zeros.

Authorizations

apiKeyAuth
basicAuth

Responses

200

Aggregated usage, or all zeros when the session has no process yet

*/*

object

404

No active session

*/*

A refusal from the chat surface: the word error and the reason, written to be shown

object

message

required

What was refused and why, such as no open stream, no active session, or an unknown command

string

status

required

Always error. A client may branch on it rather than on the status code

string

Example

error