OctoAI

概览

OctoAI, which began as OctoML, sold hosted inference for open image and language models built on its model-optimisation stack. NVIDIA acquired the company in 2024 and closed the public OctoAI service.

Acquired by NVIDIA in 2024; the hosted service was discontinued and octo.ai now redirects to nvidia.com (checked 2026-10-11).

方案与价格

GPU型号

类似服务商

NebiusAmsterdam-based AI cloud with GB300/B300/H200 capacity and Token Factory inferenceimmers.cloudMoscow GPU cloud with immersion-cooled servers and per-second billingDenvr DataworksCanadian AI cloud with sovereign GPU compute in Canada and the USTogether AIOpen-model inference API plus self-serve and reserved NVIDIA GPU clustersIntelion CloudMoscow GPU cloud with per-second billing, H200/H100 SXM and 48GB RTX 4090 cardsCloud.ruSber's cloud provider (ex-SberCloud) with Evolution IaaS/PaaS and GPU rentalfalGenerative media platform with pay-per-use model APIs and serverless GPUsFriendliAIInference platform with model APIs, per-second dedicated GPUs and bring-your-own-GPU