Usage

Usage explains what your organization consumed. Billing explains the balance, plan, rentals, and invoices that pay for it. The public usage surface has three views:

View	What it answers
Metrics	How much session and inference usage occurred in a reporting window?
Sessions	Which phone sessions contributed time and cost?
Inferences	Which vision calls contributed cost and latency?

Aggregate metrics

Dashboard
CLI
Python SDK
Go SDK
REST API

Open Usage → Sessions or Usage → Inferences after choosing your organization. Each view combines an aggregate chart with the rows for its selected date range. Billing shows total usage spend.

axilio usage metrics \
  --from 2026-08-01 \
  --to 2026-08-28 \
  --granularity daily

Add -o json for the chart series as well as the summary.

from datetime import datetime, timezone

start = datetime(2026, 8, 1, tzinfo=timezone.utc)
end = datetime(2026, 8, 28, tzinfo=timezone.utc)

metrics = client.usage.get_metrics(
    start_date=start,
    end_date=end,
    granularity="daily",
    timezone="America/Chicago",
)
print(metrics.cost_by_product.sessions)
print(metrics.cost_by_product.inference)

metrics, err := api.Usage.GetMetrics(ctx, &platformgo.UsageGetMetricsRequest{
    StartDate:   platformgo.MustParseDateTime("2026-08-01T00:00:00Z"),
    EndDate:     platformgo.MustParseDateTime("2026-08-28T00:00:00Z"),
    Granularity: platformgo.UsageGetMetricsRequestGranularityDaily.Ptr(),
    Timezone:    platformgo.String("America/Chicago"),
})
if err != nil {
    log.Fatal(err)
}
fmt.Println(metrics.CostByProduct.Sessions, metrics.CostByProduct.Inference)

REST API References:

Get usage metrics: GET /usage/metrics

curl --silent --show-error --fail-with-body \
  --url "https://api.axilio.ai/api/v1/usage/metrics?start_date=2026-08-01T00%3A00%3A00Z&end_date=2026-08-28T00%3A00%3A00Z&granularity=daily" \
  --header "X-Axilio-Api-Key: $AXILIO_API_KEY"

Session usage

Session usage includes lifecycle, allocation source, phone time, inference cost, and billing processing state for each phone session.

Dashboard
Python SDK
Go SDK
REST API

Open Usage → Sessions, then filter by session status, billing state, allocation source, or date. Search can match a session or workflow ID.

sessions = client.usage.list_sessions(
    start_date=start,
    end_date=end,
    limit=50,
)
for session in sessions.sessions or []:
    print(session.session_id, session.total_cost_microdollars)

sessions, err := api.Usage.ListSessions(ctx, &platformgo.UsageListSessionsRequest{
    StartDate: platformgo.MustParseDateTime("2026-08-01T00:00:00Z"),
    EndDate:   platformgo.MustParseDateTime("2026-08-28T00:00:00Z"),
    Limit:     platformgo.Int64(50),
})

REST API References:

List phone sessions with cost: GET /usage/sessions

curl --silent --show-error --fail-with-body \
  --url "https://api.axilio.ai/api/v1/usage/sessions?start_date=2026-08-01T00%3A00%3A00Z&end_date=2026-08-28T00%3A00%3A00Z&limit=50" \
  --header "X-Axilio-Api-Key: $AXILIO_API_KEY"

Filter, order, and page session usage

start_date and end_date are required RFC 3339 timestamps. A session-usage request also supports:

session_status_filter;
processed_status_filter;
workflow_id;
allocated_by;
search;
limit from 1 through 100, defaulting to 50; and
a nonnegative offset, defaulting to 0.

Use order_by with one of allocated_at, deallocated_at, duration, cost_microdollars, session_status, processed_status, allocated_by, session_id, or workflow_id, followed optionally by asc or desc. The default is allocated_at desc. The response contains sessions, total, limit, and offset. Continue requesting pages until you have consumed total. Each row identifies the session, workflow, and phone and reports session, inference, and total microdollar cost. It can also include allocation and deallocation time, duration, session and processing status, billing plan, allocation source, and session metadata. An interactive pending session can use an empty workflow_id because it was not created by a workflow.

Read processed_status before interpreting cost. A numeric zero on a pending row is not proof that the finalized session was free. Inference-cost lookup is also best effort, so a point-in-time total can temporarily omit an inference component.

The CLI currently exposes aggregate metrics and inference rows, but not the session-usage table. Use the dashboard, an SDK, or REST for this view.

Inference usage

Dashboard
CLI
Python SDK
Go SDK
REST API

Open Usage → Inferences. Filter by endpoint, model, or date, and use search to find an ID.

axilio usage inferences \
  --from 2026-08-01 \
  --to 2026-08-28 \
  --endpoint locate \
  --limit 50

inferences = client.usage.list_inferences(
    start_date=start,
    end_date=end,
    endpoint_filter=["locate"],
    limit=50,
)
for inference in inferences.inferences or []:
    print(inference.inference_id, inference.cost_microdollars)

inferences, err := api.Usage.ListInferences(
    ctx,
    &platformgo.UsageListInferencesRequest{
        StartDate:      platformgo.MustParseDateTime("2026-08-01T00:00:00Z"),
        EndDate:        platformgo.MustParseDateTime("2026-08-28T00:00:00Z"),
        EndpointFilter: []string{"locate"},
        Limit:          platformgo.Int64(50),
    },
)

REST API References:

List inference calls: GET /usage/inferences

curl --silent --show-error --fail-with-body \
  --url "https://api.axilio.ai/api/v1/usage/inferences?start_date=2026-08-01T00%3A00%3A00Z&end_date=2026-08-28T00%3A00%3A00Z&endpoint_filter=locate&limit=50" \
  --header "X-Axilio-Api-Key: $AXILIO_API_KEY"

Aggregate cost_by_product values are US dollars. Session and inference row fields whose names end in _microdollars use microdollars. One US dollar equals 1,000,000 microdollars.

Next steps

Telemetry dashboard

Relate point-in-time operation costs to one session’s execution.

Billing

Understand dedicated rentals, balance, and payment actions.

Balance, credits, and invoices

Understand credit lifecycle, configure alerts, and download invoice PDFs.

Get Started

Phones and Sessions

Workflows and Runs

Files

Observability

Telemetry

Billing

Organization

Reference

Usage

Aggregate metrics

Session usage

Filter, order, and page session usage

Inference usage

Next steps

Telemetry dashboard

Billing

Balance, credits, and invoices

​Aggregate metrics

​Session usage

​Filter, order, and page session usage

​Inference usage

​Next steps

Telemetry dashboard

Billing

Balance, credits, and invoices

Aggregate metrics

Session usage

Filter, order, and page session usage

Inference usage

Next steps