List metrics

Serves the invocations-over-time histogram for the org's Agents dashboard.

GET /v1/agent/metrics

Agent → · All API references → · Get started →

Address	`https://api.hanzo.ai/v1/agent/metrics`
Method	`GET`
Operation	`get_agent_metrics`
Auth	`Authorization: Bearer $HANZO_API_KEY`

Serves the invocations-over-time histogram for the org's Agents dashboard. Every point is a REAL count of recorded runs in that time bucket — one series line per agent that ran in the window. The Resource Usage rollup is all-null because this store meters no CPU/memory/storage/cost; the console renders those as "—" rather than a fabricated figure. No runs => empty series (an honest "not connected / no activity yet"), never a synthesized trend.

Request

1 field.

Field	In	Type	Required	Description
`range`	query	string	—	Range is the window to bucket: 24H, 7D or 30D.

Response

Status	Body	Meaning
`200`	agent.metricsView	ok
`default`	problem-details	refused

200 body — 11 fields.

Field	In	Type	Always	Description
`range`	body	string	—	echoes the requested window (24H\|7D\|30D)
`resource`	body	agent.resourceUsage	—
`resource.costCents`	body	number (double)	—	CostCents would be the window's spend in cents.
`resource.cpuVcpuHours`	body	number (double)	—	CPUVcpuHours would be vCPU-hours over the window.
`resource.memGbHours`	body	number (double)	—	MemGbHours would be gigabyte-hours of memory.
`resource.storageIoBytes`	body	number (double)	—	StorageIoBytes would be bytes moved to and from storage.
`series`	body	agent.seriesLine[]	—	per-agent invocation histogram (real)
`series[].key`	body	string	—	agent name
`series[].points`	body	agent.seriesPoint[]	—	Points is one bucket per interval across the whole window, in time order and never sparse: a bucket with no runs is present with v 0, so two lines drawn from two agents share an x-axis without the client aligning anything.
`series[].points[].t`	body	string	—	bucket start, RFC3339 UTC
`series[].points[].v`	body	integer (int64)	—	real invocation count in the bucket

Failure carries the platform error shape — see Errors.

Examples

CLI

SDK

HTTP

MCP

hanzo agent metrics

.ts

.py

.go

.rs

.java

import { Configuration, AgentApi } from 'hanzoai';

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

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

client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = AgentApi(client).get_agent_metrics()

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

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

use hanzo_client::apis::{configuration::Configuration, agent_api};

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

let result = agent_api::get_agent_metrics(&cfg, Default::default()).await?;

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

ApiClient client = new ApiClient();
client.setBearerToken(System.getenv("HANZO_API_KEY"));

var result = new AgentApi(client).getAgentMetrics();

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

MCP reaches agent through the agent tool, which names its 38 operations with its own verbs — this one among them, under a name only MCP 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_agents"
         }
       }
     }'

Agent API · All Hanzo APIs · Interactive reference

Was this page useful?

PreviousList tree — GET /v1/agent/coding/{session}/tree NextList runs — GET /v1/agent/runs