Burning $130K/Day? Unpacking DeepSeek API Token Volumes
teortaxesTex · x · 2026-08-05
Responding to claims that OpenCode users spend $130K daily on DeepSeek, developer teortaxesTex provided a technical breakdown using his own first-party session data:
- Cost Reverse Calculation: At $5 per million tokens, $130K translates to roughly 26 Trillion tokens consumed per day.
- Cache Hit Rate is Key: DeepSeek's ability to handle such massive volume relies heavily on an exceptionally high cache hit rate of over 99%.
- Data Discrepancy: OpenCode officially reported around 6 Trillion tokens, showing a significant gap from the estimated 26T, suggesting the original claim might be inflated or use different measurement criteria.
Related event: DeepSeek Inference Costs Revealed: Global Daily Spend Around $140k(2 posts)→
More from Infra
- Trading 2 RTX 5090s for 4 R9700s: does doubled VRAM pay off? — poofph · 2026-10-16
- Running PolyStrata + Cline coding agent on a $0-fancy laptop at ~90 tok/s — rpwoerk · 2026-10-16
- TensorFold 1.0.12 runs 120B vision model on 1-2 DGX Sparks, adds Mac image input — HankYeomans · 2026-10-16
- vLLM brings frontier model local deployment to NVIDIA RTX Spark PCs — vllm_project · 2026-10-16
- NVIDIA signals $2B in new European AI deals at GTC Berlin, totaling ~$10B in a year — CurieuxExplorer · 2026-10-16
- Making Your Data Ready for Agentic AI: trust first, then semantics, then writes — bibryam · 2026-10-16