Model access

DeepSeek V4.1 Flash reaches OpenClaw, NEAR AI Cloud and Project Maya

openclaw announced that DeepSeek V4.1 Flash is available in OpenClaw, while NEARProtocol said that the model had gone live on NEAR AI Cloud. NEARProtocol cautioned that users seeking fully private inference should look for models designated Private TEE in its catalog.

PeasantSmith said that Project Maya v1.1.22 allows DeepSeek-V4.1-Flash-1017 to run fully on a 128GB PC and includes decoding and prompt-processing improvements. Separately, rlaope promoted an UltraFast service on OpenGateway, claiming a maximum streaming rate of 848+ tokens per second.