RightNow Launches Inference API on Its Self-Developed Fastest Engine

iconKuCoinFlash
Share
AI summary iconSummary
RightNow has launched a new inference API on its fastest self-developed engine, MetaEra, as part of its ongoing on-chain news updates. The API claims to enhance GPU performance, with NVIDIA reporting a 14x speed improvement via its kernel. Half of the open model inference market already utilizes this kernel. The service provides access to leading open models and charges on a per-token basis, though the model list, benchmarks, and pricing have not been disclosed. This token launch underscores a significant development in the AI inference space.
ME AI message: RightNow announced on Twitter that its technology enables AI models to run faster on GPUs. The company claims that half of the open model inference market already uses its kernel, and NVIDIA achieved a 14x performance improvement using it. On the same day, RightNow launched its own inference API, running on its fastest engine, offering top-performing open models at full speed with pay-per-token billing. The original text did not disclose the list of models, performance benchmark details, pricing, or availability. (Source: InFoQ)
Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information. Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.