RightNow launches inference API, claims 14x NVIDIA performance via GPU kernels
ycombinator · x · 2026-11-17
Y Combinator-backed RightNow AI launched its own inference API built on GPU kernel-level optimizations, claiming half the open-weight inference market already uses its kernels and that NVIDIA saw 14x performance gains with them.
The API offers pay-per-token pricing, batch at half price, reserved capacity, and dedicated deployments with zero data retention by default. Listed models include DeepSeek V4.1 Flash ($0.15/M input, $0.60/M output, 327 tok/s), GLM 5.3 and GLM 5.3 Flash, and NVIDIA Nemotron 3.5 Lightning 30B (540 tok/s), with cache hit rates above 93%.
More from Venture
- Healthcare AI spend hits $3.7B, drug discovery AI surges 23x: Menlo Ventures report — mmurph · 2026-11-17
- August raises $12M from Accel and Peak XV as its AI spends 24,286 minutes on hold booking doctor visits — anthara_ai · 2026-11-17
- Europe leads in image, audio, video and app generation — but its AI companies find customers stateside — nathanbenaich · 2026-11-17
- Solo founder loses tens of thousands to token fraud, shares her full counter-fraud playbook — annetgriffin · 2026-11-17
- PathRobotics raises $300M at $2.45B as ARR grows 17x in 18 months — lukas_m_ziegler · 2026-11-17
- Agile Robots raises $500M at $8.5B, Europe's most valuable robotics startup — lukas_m_ziegler · 2026-11-17