Privacy-Preserving Dashboard

AI Token Burn Dashboard

A public-safe view of human-directed AI usage: model routes, daily token totals, cost estimates, and aggregate operating signals. It deliberately excludes prompts, responses, session names, file paths, private work details, heartbeat polls, cron jobs, and subagent bootstrap traffic.

Source: human-directed OpenClaw usage logsTimezone: America/New_YorkUpdated: 6/28/2026, 6:20:48 AM

Total tokens

542.2M

5,480 human-directed calls

Active days

48

11.3M avg tokens/day

Model mix

4

distinct model routes

Estimated cost

$0.00

from local usage metadata

Daily Human-Directed Token Burn

GitHub-style activity map. Click a day to inspect model-level usage.

May 7, 2026 - Jun 28, 2026
LessMore

May 9, 2026

60.8M tokens

Input6,978,170
Output17,175
Cache read53,800,319
Cache write0

Calls

908

Cost

$0.00

Model Breakdown

openrouter/auto
908 calls ยท $0.00
60.8M

All-Time Model Mix

openai/gpt-5.557%
nvidia/nemotron-3-super-120b-a12b:free28%
openrouter/auto15%
google/gemma-4-31b-it:free0%

Operational Signals

Output share

0%

Cache share

64%

Peak day

May 9, 2026

Top route

openai/gpt-5.5

This is intentionally a usage telemetry view, not a conversation archive. It shows where human-directed compute is going without exposing the work itself.

Accounting Scope

Counted records

5,480

Excluded records

647

Timestamp basis

OpenClaw local record timestamp

Human-directed turns only.

Privacy Boundary

The published data file contains only daily aggregate human-directed usage by model: input tokens, output tokens, cache tokens, call counts, and cost estimates when available. Automated heartbeat polls, cron jobs, and subagent bootstrap sessions are excluded. Raw conversations and local session identifiers stay on the OpenClaw workstation.