If you bounce between Claude Code, OpenAI Codex CLI, Google Antigravity, OpenCode, xAI Grok CLI, and Cline / Roo Code, you quickly run into a blind spot: every agent stores local token telemetry in a completely different format — and even uses incompatible prompt-cache accounting rules.
-
Anthropic / Antigravity / OpenCode log uncached input,
cache_read, andcache_writeas separate additive buckets (total_input = input + cache_read + cache_write). -
OpenAI / Codex CLI / Grok CLI log
cached_tokensas an inclusive subset already insideinput_tokens(plus Codex silently compresses older sessions into~/.codex/archived_sessions/*.jsonl.zst, while OpenCode v2 migrated from JSON files to a local SQLiteopencode.db).
To see my real 30-day token burn without uploading a single prompt or file path anywhere, I built a zero-dependency, 100% read-only Python stdlib auditor (audit_ai_spend.py) + an open-source API vs. GPU Break-Even Calculator.
Run It in 1 Command (Zero pip install, 100% Local Read-Only)
curl -fsSL https://ai-cost-radar-nlu.pages.dev/audit_ai_spend.py | python3 - --days 30 --lang en --region global
(Security tip: you can inspect the script first with curl -fsSL https://ai-cost-radar-nlu.pages.dev/audit_ai_spend.py | less — it uses only Python's standard library json, sqlite3 in ?mode=ro read-only URI mode, and in-memory zstd decoding.)
Supported Local Coding & Agent Clients
| Client | Local Telemetry Source | Accounting Nuance Handled |
|---|---|---|
| Claude Code | ~/.claude/projects/**/*.jsonl |
Streaming message.id dedupe + additive cache math |
| OpenAI Codex |
~/.codex/sessions/**/*.jsonl + archived_sessions/*.jsonl.zst
|
In-memory .zst decode + response_id retry dedupe (skips duplicate event_msg:token_count) |
| Google Antigravity | ~/.gemini/antigravity/brain/*/.system_generated/logs/transcript.jsonl |
Reads PLANNER_RESPONSE steps & skips transcript_full.jsonl to prevent 2x double-counting |
| OpenCode |
~/.local/share/opencode/opencode.db + legacy JSON |
Read-only SQLite ?mode=ro with per-row timestamp cutoff + legacy JSON ID dedupe |
| xAI Grok CLI |
~/.grok/sessions/*/*/updates.jsonl + summary.json
|
Filters turn_completed events with inclusive inputTokens + cacheCreationTokens
|
| Cline / Roo Code | globalStorage/.../tasks/*/ui_messages.json |
Extracts api_req_started cost & additive cache reads/writes |
| WorkBuddy / Qwen |
~/.workbuddy, ~/.codebuddy, ~/.qwen, ~/.qoder
|
Multi-turn JSONL & read-only SQLite session aggregation |
3 Surprises From Auditing 47,000+ Real Local Agent Calls
-
Codex
.jsonl.zstarchives hide most of your 30-day history: Scanning only uncompressed~/.codex/sessionsmissed over 60% of my 30-day Codex calls that had been rotated into.jsonl.zst. - 90%+ prompt-cache hit rates completely change the API vs. Self-Hosted GPU math: Naive token calculators multiply total context tokens by full uncached input rates, overestimating agent bills by 4x–6x. Once you account for real cache read discounts, renting a dedicated 24GB GPU pod (e.g., RTX 4090 / A100 on RunPod) only beats Pay-As-You-Go APIs when post-cache spend crosses ~$125/month — below that, Pay-As-You-Go or a lightweight ~$5/month LiteLLM semantic-cache proxy wins.
-
A single runaway debug loop can eat 25% of your monthly budget: In the companion web tool, you can drag-and-drop multiple
.jsonl/.csvlogs locally in your browser (zero server upload) and toggle "Exclude #1 Spike Session" to compare your steady-state daily burn and export a zero-codeLiteLLM config.yaml.
Try the Interactive Calculator & Source Code
- Live Calculator & Spend Auditor (English / USD): https://ai-cost-radar-nlu.pages.dev/ai-coding-spend-auditor/
- GitHub Repository (MIT, Python 3.12+ stdlib + Vanilla ES2024): https://github.com/huangbuqubunao-alt/ai-cost-radar
(Transparency note: the open-source repo has zero trackers; selected cloud host cards on the web directory may carry partner referral links at identical official catalog prices.)
If your daily-driver coding CLI stores token logs in another path or schema, drop a comment below and I'll add exact parser support for it!
Top comments (0)