Skip to main content
GET
/
api
/
v1
/
overview
Overview Analytics
curl --request GET \
  --url https://api.example.com/api/v1/overview
{
  "summary": {
    "tokens_today": {
      "value": 123,
      "trend_pct": 123,
      "sub_values": {
        "input": 123,
        "output": 123
      }
    },
    "cost_today": {
      "value": 123,
      "trend_pct": 123
    },
    "messages": {
      "value": 123,
      "trend_pct": 123
    },
    "services_hit": {
      "total": 123,
      "healthy": 123,
      "issues": 123
    }
  },
  "token_usage": [
    {
      "hour": "<string>",
      "date": "<string>",
      "input_tokens": 123,
      "output_tokens": 123
    }
  ],
  "cost_usage": [
    {
      "hour": "<string>",
      "date": "<string>",
      "cost": 123
    }
  ],
  "message_usage": [
    {
      "hour": "<string>",
      "date": "<string>",
      "count": 123
    }
  ],
  "cost_by_model": [
    {
      "model": "<string>",
      "tokens": 123,
      "share_pct": 123,
      "estimated_cost": 123
    }
  ],
  "recent_activity": [
    {
      "id": "<string>",
      "timestamp": "<string>",
      "agent_name": "<string>",
      "model": "<string>",
      "input_tokens": 123,
      "output_tokens": 123,
      "total_tokens": 123,
      "cost": {},
      "status": "<string>",
      "routing_tier": {},
      "routing_reason": {},
      "error_message": {}
    }
  ],
  "active_skills": [
    {
      "name": "<string>",
      "agent_name": {},
      "run_count": 123,
      "last_active_at": "<string>",
      "status": "<string>"
    }
  ],
  "has_data": true
}

​
Overview

The overview endpoint provides a complete snapshot of your agent’s performance metrics. It returns summary statistics, timeseries data for tokens/costs/messages, cost breakdown by model, recent activity, and active skills. This endpoint intelligently switches between hourly and daily aggregations based on the selected time range, providing optimal granularity for visualization.

​
Authentication

Requires session authentication (cookie) or API key via X-API-Key header.

​
Query Parameters

​
range
string
default:"24h"
Time range for analytics. Valid values: 1h, 6h, 24h, 7d, 30d
  • Hourly data returned for: 1h, 6h, 24h
  • Daily data returned for: 7d, 30d
​
agent_name
string
Filter analytics to a specific agent. If omitted, returns data for all agents.

​
Response Schema

​
summary
object
High-level metrics for the selected time range
​
token_usage
array
Timeseries data for token usage (hourly or daily based on range)
​
cost_usage
array
Timeseries data for costs (hourly or daily based on range)
​
message_usage
array
Timeseries data for message counts (hourly or daily based on range)
​
cost_by_model
array
Cost and token breakdown by model, ordered by token usage
​
recent_activity
array
Last 5 messages in the time range, ordered by timestamp descending
​
active_skills
array
Skills that were executed in the time range, ordered by run count
​
has_data
boolean
Whether any telemetry data exists for this user/agent

​
Example Request

cURL
curl -X GET "https://api.manifest.build/api/v1/overview?range=24h&agent_name=my-agent" \
  -H "X-API-Key: your-api-key"

​
Example Response

{
  "summary": {
    "tokens_today": {
      "value": 125840,
      "trend_pct": 12.5,
      "sub_values": {
        "input": 85000,
        "output": 40840
      }
    },
    "cost_today": {
      "value": 0.45,
      "trend_pct": 8.2
    },
    "messages": {
      "value": 42,
      "trend_pct": -5.0
    },
    "services_hit": {
      "total": 0,
      "healthy": 0,
      "issues": 0
    }
  },
  "token_usage": [
    {
      "hour": "2026-03-04 00:00:00",
      "input_tokens": 3500,
      "output_tokens": 1200
    },
    {
      "hour": "2026-03-04 01:00:00",
      "input_tokens": 4200,
      "output_tokens": 1800
    }
  ],
  "cost_usage": [
    {
      "hour": "2026-03-04 00:00:00",
      "cost": 0.018
    },
    {
      "hour": "2026-03-04 01:00:00",
      "cost": 0.024
    }
  ],
  "message_usage": [
    {
      "hour": "2026-03-04 00:00:00",
      "count": 5
    },
    {
      "hour": "2026-03-04 01:00:00",
      "count": 8
    }
  ],
  "cost_by_model": [
    {
      "model": "claude-4.5-sonnet",
      "tokens": 95000,
      "share_pct": 75.5,
      "estimated_cost": 0.32
    },
    {
      "model": "gpt-4o",
      "tokens": 30840,
      "share_pct": 24.5,
      "estimated_cost": 0.13
    }
  ],
  "recent_activity": [
    {
      "id": "msg_abc123",
      "timestamp": "2026-03-04T10:30:00Z",
      "agent_name": "my-agent",
      "model": "claude-4.5-sonnet",
      "input_tokens": 2500,
      "output_tokens": 1200,
      "total_tokens": 3700,
      "cost": 0.015,
      "status": "ok",
      "routing_tier": "smart",
      "routing_reason": "complex_task",
      "error_message": null
    }
  ],
  "active_skills": [
    {
      "name": "web-search",
      "agent_name": "my-agent",
      "run_count": 15,
      "last_active_at": "2026-03-04T10:25:00Z",
      "status": "active"
    }
  ],
  "has_data": true
}

​
Notes

  • Trend calculations: Compares current period vs. previous period of equal length. For example, 24h range compares last 24 hours vs. previous 24 hours.
  • Hourly vs. Daily: Ranges 1h, 6h, 24h return hourly timeseries. Ranges 7d, 30d return daily timeseries.
  • Caching: Responses are cached for 5 minutes (see DASHBOARD_CACHE_TTL_MS).
  • Multi-tenancy: Data is automatically filtered by authenticated user. Users only see their own agents’ data.
  • Cost sanitization: Negative costs (invalid pricing data) are treated as 0.

Build docs developers (and LLMs) love

Get started for freeTalk to us