Is the entitlement-GATED per-provider breakdown of the caller org's LLM usage —…

Is the entitlement-GATED per-provider breakdown of the caller org's LLM usage — the paid lens over the same warehouse ledger GET /v1/usage/summary reads…

GET /v1/usage/analytics

Usage → · All API references → · Six flows, four surfaces →


Address	`https://api.hanzo.ai/v1/usage/analytics`
Method	`GET`
Operation	`get_usage_analytics`
Auth	`Authorization: Bearer $HANZO_API_KEY`

Is the entitlement-GATED per-provider breakdown of the caller org's LLM usage — the paid lens over the same warehouse ledger GET /v1/usage/summary reads its totals from. Basic own-org usage stays ungated at /v1/usage/summary.

A plan that does not grant the analytics datastore is refused with 402, and an unresolvable plan fails closed to the free floor, which does not grant it. The window is clamped forward to the plan's retention entitlement, so a tenant can never read older than its plan allows even with a custom start. The response is marked no-store.

INTERIM (mirrors apps/world's limits echo): no org→plan resolver exists in cloud yet — the subscription lookup is owned by the billing plane and the gateway principal carries no plan claim — so the caller passes the plan and the gate resolves THAT plan's access.

Request

4 fields.

Field	In	Type	Required	Description
`end`	query	string	—	End is the exclusive window end, RFC3339.
`plan`	query	string	—	Plan is the plan id whose entitlement decides access and retention.
`range`	query	string	—	Range is the window: a count and a unit — 24h, 7d, 90d, any <N>h or <N>d — or day, week, month, all, custom. Empty means 24h.
`start`	query	string	—	Start is the inclusive window start, RFC3339.

Response

Status	Body	Meaning
`200`	usageAnalyticsView	ok

200 body — 17 fields.

Field	In	Type	Always	Description
`end`	body	string	—	End is the window's exclusive end, RFC3339 UTC.
`export`	body	boolean	—	Export is whether the resolved plan allows exporting these rows.
`plan`	body	string	—	Plan echoes the plan id the entitlement was resolved from.
`providers`	body	ProviderBreakdown	—
`providers.available`	body	boolean	—	Available is false when the warehouse could not be read, which means "no answer" and NOT "no usage" — Items is then empty for a reason.
`providers.items`	body	ProviderRow[]	—	Items is one row per provider, most tokens first.
`providers.items[].costCents`	body	integer	—	CostCents is what they cost the org, in US cents.
`providers.items[].provider`	body	string	—	Provider is the upstream the requests were routed to, e.g.
`providers.items[].requests`	body	integer	—	Requests is how many completions the org made against that provider.
`providers.items[].tokens`	body	integer	—	Tokens is the total tokens those completions consumed, prompt plus completion.
`providers.source`	body	string	—	Source names the warehouse table the rows came from.
`range`	body	string	—	Range is the label that was ASKED for. A plan whose retention is shorter than that window is served the retention instead, so read start and end for the window…
`retentionDays`	body	integer	—	RetentionDays is how far back the resolved plan allows reading.
`scope`	body	usageScope	—
`scope.org`	body	string	—	Org is the IAM org slug the rows were read under — the validated principal's, never a client header.
`scope.user`	body	string	—	User is the caller's own subject, whose linked-account rows the accounts block carries.
`start`	body	string	—	Start is the window's inclusive start, RFC3339 UTC, AFTER the retention clamp — so it may be later than the start that was asked for.

Failure carries the platform error shape — see Errors.

Examples

hanzo usage analytics get

import { Configuration, UsageApi } from 'hanzoai';

const api = new UsageApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.getUsageAnalytics();

from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import UsageApi

client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = UsageApi(client).get_usage_analytics()

cfg := cloud.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := cloud.NewAPIClient(cfg)

resp, _, err := client.UsageAPI.GetUsageAnalytics(context.Background()).Execute()
if err != nil {
	return err
}

use hanzo_cloud::apis::{configuration::Configuration, usage_api};

let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();

let result = usage_api::get_usage_analytics(&cfg, Default::default()).await?;

import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.UsageApi;

ApiClient client = new ApiClient();
client.setRequestInterceptor(b -> b.header("Authorization", "Bearer " + System.getenv("HANZO_API_KEY")));

var result = new UsageApi(client).getUsageAnalytics();

curl https://api.hanzo.ai/v1/usage/analytics \
  -H "Authorization: Bearer $HANZO_API_KEY"

The door reaches usage through the usage tool, which names its 5 operations with its own verbs — this one among them, under a name only the door declares. describe explains any of them:

curl -X POST https://api.hanzo.ai/v1/mcp \
  -H "Content-Type: application/json" \
  -d '{
       "jsonrpc": "2.0",
       "id": 1,
       "method": "tools/call",
       "params": {
         "name": "describe",
         "arguments": {
           "op": "list_usage_analytics"
         }
       }
     }'

Usage API · All Hanzo APIs · Interactive reference

Is the entitlement-GATED per-provider breakdown of the caller org's LLM usage —…

Request

Response

Examples

On this page