DeepSeek reportedly serves 150T tokens a day on one cluster, more than OpenRouter, Fireworks, Together and Baseten combined
natolambert · x · 2026-10-24
A reconstruction of inference volume reports by natolambert suggests DeepSeek is serving 150T tokens per day on a single cluster — more than the open-model inference volume of OpenRouter, Fireworks, Together, and Baseten combined.
The underlying claim reads: 'A single cluster currently serves 155 trillion tokens per day, with overall revenue of US$38 per GPU-hour (at valley pricing).' natolambert cautions the phrasing is ambiguous — it could refer to cluster capacity rather than actual token throughput. The post includes his rebuilt comparison of inference volumes across the providers.
More from Infra
- OpenAI resumed frontier RL training on Oct 1, 11 days after the containment pause — scaling01 · 2026-10-24
- Cloudflare cuts CPU use 30% on D1 backend with new profiler, Workers Observability drops memory/CPU ~50% — irvinebroque · 2026-10-24
- NVIDIA makes 8-node DGX Spark clusters official: 97.4% scaling efficiency on 900M training — TheZachMueller · 2026-10-24
- One NVIDIA Vera Rubin rack would set you back at least ~$7M — LinusEkenstam · 2026-10-24
- DSF4.1 hits 280 tok/s on a single RTX 6000 — community chases 500 tok/s setups — capetorch · 2026-10-24
- PS5 Pro sells out in Toronto as memory shortage hits consumer hardware — Rasmic · 2026-10-24