Prime Inference hits 120B tokens/day on OpenRouter one month after launch, powered by vLLM
woosuk_k · x · 2026-10-29
Prime Inference has scaled from zero to 120 billion tokens served daily on OpenRouter within just one month of onboarding — and that's only a small portion of its total traffic. The inference service runs open models at scale powered by the open-source vLLM project, with team members highlighting the milestone.
Related event: Prime Inference Hits 120B Daily Tokens One Month After OpenRouter Launch(3 posts)→
More from Infra
- Beam integrates with Hugging Face to move million-scale datasets over its distributed network — markjeffrey · 2026-10-29
- Qwen3.5-4B hits ~11.4 tok/s CPU-only on a Ryzen 5 laptop with llama.cpp tuning — solyarisoftware · 2026-10-29
- Microsoft's 4,800-person layoffs save what its AI data center spend burns in two days — aakashgupta · 2026-10-29
- Strix Halo-specific kernels speed up vLLM prefill by up to 31x at long context — asfbrz96 · 2026-10-29
- FuriosaAI quadruples valuation to $2.9B in new funding round to challenge Nvidia — dinabass · 2026-10-29
- Dev questions Anthropic ops: Claude Code source leaked to prod, backbone outages 'routine' — cuenca · 2026-10-29