OpenRouter crosses 400T monthly inference tokens, up ~27x in a year
gajesh · x · 2026-09-07
OpenRouter's monthly inference volume crossed 400 trillion tokens this weekend, up from just 15T at the same time last year — a roughly 26x year-over-year increase that reflects the explosive growth in LLM inference usage.
Related event: OpenRouter Monthly Inference Hits 400T Tokens, Up 27x Year-Over-Year(2 posts)→
More from Infra
- RTX 5080 price jumps from $1658 to $2318 in ten days on Amazon — Frizzy-MacDrizzle · 2026-10-27
- ComfyUI on 12GB VRAM: measured peaks show offloading turns 24s into 11 minutes — Impossible-Mail-4619 · 2026-10-27
- Neon rebuilds its docs search entirely on its own stack: Lakebase Search, Functions, AI Gateway — matei_zaharia · 2026-10-27
- PyTorch details 2.12x faster on-device streaming ASR on Arm SME2 via ExecuTorch — PyTorch · 2026-10-27
- NVIDIA shows speculative decoding speeding up LLM inference on Jetson with Qwen3.5 9B — NVIDIA Developer · 2026-10-27
- Revenue per GPU can rise as token prices fall, argues Gavin Baker — GavinSBaker · 2026-10-27