Tradução do inglês. Em caso de divergência, prevalece a versão em inglês.
Pune, India
Region dependent, Multiple / Unspecified
São Paulo State, Brazil
Seoul, South Korea
Silicon Valley, United States
Singapore, Singapore
Texas, United States
Thailand (location unspecified), Thailand
Tokyo, Japan
Toronto, Canada
United States, United States
Unspecified, Multiple / Unspecified
Vienna, Austria
Vietnam (location unspecified), Vietnam
Virginia, United States
Warsaw, Poland
Washington State, United States
Wyoming, United States
Zagreb, Croatia
Zurich, Switzerland
Acesso à oferta
Todos os tipos de acesso Autoatendimento / lançamento Publicado / documentado Contato / reserva Oferta variável / cotação ao vivo Indisponível Outro / não especificado
Contrato Todos os tipos de contrato On-demand Spot / preemptible Reserved / comprometido Serverless / inferência Cotação / pré-venda Outro / não especificado
Publicly listed
Publicly priced; regional capacity varies
Published configuration; live capacity unconfirmed
Published starting price; capacity unconfirmed
Published starting price; live capacity unconfirmed
Published starting service rate; allocation and live capacity unconfirmed
Quote or tariff confirmation required; live capacity unconfirmed
Reserve / request quote
Reserve bare metal
Reserved capacity / contact workflow
Reserved only
Self-serve
Self-serve first-come
Self-serve; capacity varies
Self-service
SKU availability not inferred from retail pricing API
Spot inventory
Spot plan offered in documented datacenter; live capacity unknown
Spot; capacity varies
Starting-price plan; location availability varies
Unconfirmed
Unknown
Contrato exato do provedor Qualquer contrato registrado 1 year+ 12-month reserved 2 weeks–1 year Capacity Block Committed Dedicated monthly Flex-start Inference platform On-Demand On-demand cluster Pre-order Preemptible Private Quote Reserved Reserved / contractual Serverless Serverless spot Spot
Tipo de implantação Qualquer implantação 1-Click Cluster Azure GPU VM Bare Metal Bare Metal as a Service Bare metal GPU cluster Bare metal GPU node Bare metal GPU server Bare-metal GPU server Dedicated Cluster Dedicated GPU Dedicated GPU instance Dedicated inference endpoint EC2 Capacity Block GPU as a Service GPU Cloud GPU cloud instance GPU cloud service GPU cloud VM GPU cluster GPU compute GPU Droplet GPU instance GPU instance family GPU platform GPU virtual machine GPU VM GPU VM / template Inference GPU compute Inference single GPU Instant GPU cluster Managed AI GPU resource — product scope unconfirmed Managed GPU compute instance Managed inference dedicated endpoint Marketplace GPU instance Marketplace GPU VM Metal GPU Pod GPU instance Public cloud GPU instance Reserved GPU cluster Salad Container Engine · High priority Salad Container Engine · Low priority Salad Container Engine · Lowest priority Salad Container Engine · Medium priority Salad Container Engine · portal-only GPU class Serverless container Serverless GPU worker SLURM/Kubernetes cluster Virtual GPU cluster Virtual Machine
Nível de evidência da fonte Qualquer nível A B
Dedicado Qualquer Obrigatório Excluir
Bare metal Qualquer Obrigatório Excluir
InfiniBand Qualquer Obrigatório Excluir
NVLink Qualquer Obrigatório Excluir
