RightNow AI launches open-model inference service
Understand this story
RightNow AI has launched an inference service for open models, stating that it has optimized inference down to the GPU kernel level, supporting models such as DeepSeek V4.1 Flash, GLM 5.3, Nemotron 3.5 Lightning 30B, and Qwen3.8 27B. Billing uses a pay-per-token, no-subscription shared capacity model, with new accounts receiving $1 in credit; reserved capacity and dedicated deployments for single-company use only are both listed as not yet available.
AI overview based on source reports · Updated 37 min ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIShow HN: Own your AI at full speed
A Show HN post presents a GPU-kernel-optimized inference stack for open models, listing per-million-token prices and measured speeds for models including DeepSeek V4.1 Flash, GLM 5.3, Nemotron 3.5 Lightning 30B, Qwen3.8 27B and Ornith 1.5 35B. It describes automatic best-effort prompt caching, a five-layer serving stack, and pay-as-you-go capacity, with reserved and dedicated deployments not yet offered. The API accepts Chat Completions and Messages requests, and new accounts get $1 free.
Activity for this story
Not enough continuous observations to show a trend yet.