wafer

@wafer_ai

continual inference optimization trusted by @vercel, @tavus, @brilliantorg, @ycombinator and 1500+ others

following
followers

Wafer claims No. 3 spot on OpenRouter by daily token volume

Wafer's announcement gives no token count for its claimed third-place ranking.

3 Sources, 10d ago, first seen 10d ago

Wafer reportedly reached 2 trillion tokens a day on OpenRouter

Wafer says it took four months to reach 1 trillion tokens a day, then four days to reach 2 trillion.

3 Sources, 11d ago, first seen 11d ago

You.com introduces Inference Router for on-demand access to AI models

You.com says the OpenAI-compatible API includes built-in web search, US hosting and zero data retention.

11 Sources, 18d ago, updated 18d ago

Y Combinator’s AI Office Hour Simulator reportedly switches to GLM-5.2 on Wafer

Wafer says its GLM-5.2 deployment delivered 31% lower average model latency than GPT-4.1 mini on OpenAI and 44% lower than Gemma 4 31B on Cerebras in YC’s comparison.

2 Sources, 54d ago, first seen 54d ago

Wafer announces AI performance engineering series, starting with transformer inference

Wafer says the first resource uses worked problems to connect model dimensions to deployment choices, including memory capacity, workload distribution and expected performance under stated assumptions.