AI Tool 100% Client-Side Privacy

LLM API Cost Analyzer: Understand Your AI Usage Bill

Upload API usage data to see cost by model, day, and project, cache savings, spikes, and month forecast with custom prices. 100% private in your browser.

Total Spend
$0.00
$0.0000 / call avg
Cache Savings
$0.00
0.0% hit rate
Monthly Forecast
$0.00
$0.00 / day run-rate
Total Tokens
0
0 reasoning tokens
Statistical 3σ cost spikes detected.
0 calls loaded

Model Price Table (per 1M Tokens USD)

Model Pattern (Prefix*) Prompt $/1M Completion $/1M CacheRead $/1M Action
CSV / JSON Field Mapping (comma-separated aliases)
Time:
Model:
Prompt:
Completion:
Cached:
Reasoning:
API Key:
Cost:
FX Rate (vs USD):
Input Usage Logs (CSV, JSON, JSONL)
Drag & Drop CSV or JSON usage exports here, or click to browse
Files process 100% locally in browser memory. Zero network uploads.
Daily Cost Trend (UTC)
No logs analyzed yet
Awaiting usage data. Click 'Load Realistic Sample' above.
Model Calls Prompt Tokens Completion Tokens Total Cost Spend Share
No logs analyzed yet
Date (UTC) Calls Total Tokens Daily Cost Cache Saved
No logs analyzed yet
Masked Key / Project Calls Total Tokens Total Cost Share
No logs analyzed yet
Timestamp (UTC) Model Prompt Tokens Completion Tokens Cost (USD) Flag
No logs analyzed yet
Model Migration Test
→
Batch API Discount 0%
E.g. 50% discount for asynchronous batch queues
Prompt Pruning & Compression 0% reduction
Simulate trimming instruction boilerplate & context
Simulated Run-Rate
$0.00 $0.00
-$0.00 (0% savings)

How to Audit and Reduce LLM API Spend

Large Language Model architectures bill on asymmetric multi-tier token pricing. Between differing rates for prompt input, cached prefixes, visible output, and hidden reasoning traces, raw monthly billing statements rarely make it obvious where money is going:

⚡

Prompt Caching Economics

Modern models (Claude 3.5 Sonnet, GPT-4o, DeepSeek) discount repeated prompt tokens by 80% to 90%. Decomposing cached reads highlights which endpoints leverage system prompt caching effectively.

🔍

3-Sigma Spike Outliers

Recursive agent tool calls or unbounded conversation contexts can silently trigger $5+ single requests. Our statistical 3-sigma anomaly detector flags these spikes automatically.

🔒

Private & Offline

No tokens, trace logs, or API keys ever touch remote servers. Parsing, currency conversions, and rate matrix evaluations execute 100% inside your local browser tab.

Frequently Asked Questions

Which file formats can I upload?

The analyzer automatically ingests CSV exports from OpenAI or Anthropic consoles, line-delimited JSONL trace files, and standard JSON arrays.

How are API keys and project names secured?

All sensitive keys matching API patterns (like sk-proj-... or sk-ant-...) are immediately masked client-side to only display their final 4 characters.

Can I customize token price tiers?

Yes. Open the Rates & Schema drawer to add custom model wildcards, override prompt and completion costs per 1M tokens, or import custom JSON rate schemes.