DeepSeek API Usage Analytics
Free DeepSeek API Cost Tracker
Drop your monthly CSV exports to see usage analytics
Drop your DeepSeek CSVs here or click to upload
Drop one or more months — amount-*.csv + cost-*.csv pairs, or a .zip archive
Multiple months are auto-merged · Files stay in your browser — nothing is uploaded
How It Works
1. Export Data
Go to DeepSeek Platform → Usage → Export monthly data. Each month downloads as a ZIP containing amount and cost CSVs.
2. Drag & Drop
Drag your ZIP files (or extracted CSVs) onto this page. Multiple months are automatically paired and merged.
3. View Analytics
Instantly see cost charts, per-key breakdowns, cache hit analysis, usage trends, and custom project groupings — all processed locally in your browser.
Frequently Asked Questions
No. All CSV parsing and cost computation runs entirely in your browser. Your data never leaves your device.
You can drag the ZIP archive downloaded from the DeepSeek Platform directly — no extraction needed. Or you can extract and upload the amount-*.csv and cost-*.csv files manually.
Yes. Drag all your monthly ZIP (or CSV) files at once — they will be automatically paired by filename and concatenated.
Any model listed in your DeepSeek exports. The dashboard auto-detects all models and provides a filter to view them individually or combined.
You need to upload both the amount CSV and the cost CSV for the same month. If either file is missing, cost data cannot be calculated.
It means a month has only the amount file or only the cost file — not both. Add the missing file and re-upload to resolve this.
Check the Troubleshooting section in our full User Guide. It covers common issues like CSV format errors, cache configuration, file naming conventions, and more.
Yes, each file must be under 50 MB. This prevents malicious ZIP bombs from freezing your browser. DeepSeek monthly usage exports are typically under 1 MB, so this limit should never be an issue for normal use.
Yes. Switch to the 'By Custom Projects' tab and click the gear icon to open the configuration panel. Drag API key names from the unassigned pool into your custom project groups. Your project configuration is saved in your browser's local storage.
About
Why We Built This
As our DeepSeek API calls surged, we found the official CSV billing exports nearly impossible to read at a glance. To answer questions like "which project consumed the most tokens?" and "what is our real cache hit rate?", we built our own simple, intuitive, and absolutely secure visualization dashboard.
Under the Hood: Privacy & Tech
When handling billing data, privacy is non-negotiable. That's why we chose a pure frontend architecture. Built with Next.js 16 (App Router) and React 19, powered by Papa Parse and ECharts, all CSV parsing and chart rendering happens 100% locally in your browser. No backend server, no database — your data never leaves your device. With Apple-inspired minimalist design and CSS custom property-driven dual themes, we aim to deliver the most elegant data analytics experience.
About MindRose
This project is open-sourced by Gavin Chen and the MindRose team. MindRose is a tech team focused on delivering lightweight digital solutions for small and medium manufacturers, logistics companies, and cross-border traders. We don't sell vague "digital transformation" concepts — we use AI and full-stack agile development (Next.js, React, Mendix, etc.) to deliver applications that solve real business pain points within weeks. From SEO-optimized independent e-commerce sites, to agile internal system builds, to AI agent workflow integration — we understand tech, and more importantly, we understand your business.
Let's Work Together
Looking to build a custom data dashboard for your business? Need deep AI integration into your workflows? Want modern, elegant UI/UX? Need cross-department, multi-terminal business systems? Or interested in collaborating on this open-source project?
We offer professional bottleneck diagnosis, transformation analysis, tailored business solutions, and AI-powered development and operations.
Sister Project
Also using Agnes AI API?
Open the dedicated Agnes AI usage analyzer to review token spend, model distribution, and trends with a matching browser-side workflow.