Agent token usage 14x human, driving massive compute demand
BenBajarin · x · 2026-09-02
Data from OpenRouter reveals that Agent token usage surpassed human usage in February and has since grown to 14 times that of humans. This surge is driven by the multi-turn nature of agentic sessions, frequent tool calling, and context reminders. As models improve at tool and computer usage, Agent compute consumption is projected to outpace human usage by 10x in the next 12 months.
More from Infra
- Not Diamond releases model routing method, cuts costs 20-80% — rohanpaul_ai · 2026-09-02
- Trading VRAM for FLOPs: Local Model Quantization Debate — max_paperclips · 2026-09-02
- DGX Spark Cluster vs AMD Epyc Server: A Cost-Benefit Comparison — LeftHandHaku · 2026-09-02
- User complains about dev tool hogging 98% RAM, requests local GPU support — MickeySteamboat · 2026-09-02
- Nvidia Backstop Enables $947M in Bank Loans for GPU Purchases — rohanpaul_ai · 2026-09-02
- Dell Predicts 87x Surge in AI Inference Demand by 2030, Enterprise Agents to Dominate Workloads — toptickcrypto · 2026-09-02