DeepInfra

已审核运营中
deepinfra.comUS美国始于 2013

Low-cost model inference API plus dedicated A100-to-B300 GPUs billed by the minute

推理无服务器
访问官网 价格联系方式
起价
—
GPU起价
¥5.96/GPU时
地区
0
个国家
数据中心
0
个站点
网络 (ASN)
0
个ASN
方案与价格
5
个方案

概览

DeepInfra serves hundreds of open models through a pay-per-token API and lets customers deploy custom models on dedicated GPUs (A100, H100, H200, B200, B300) billed in minute granularity, with dedicated DGX-class clusters on request.

方案与价格

GPU实例5
Instance配置每GPU小时总价 /时竞价地区来源
Dedicated A100 80GB for custom LLMs — per GPU, minute granularity
1× A100 80GB¥5.96¥5.96—
 已核实
4天前
Dedicated H100 for custom LLMs — per GPU, minute granularity
1× H100 SXM¥14.72¥14.72—
 已核实
4天前
Dedicated H200 for custom LLMs — per GPU, minute granularity
1× H200¥18.00¥18.00—
 已核实
4天前
Dedicated B200 for custom LLMs — per GPU, minute granularity
1× B200¥24.70¥24.70—
 已核实
4天前
Dedicated B300 for custom LLMs — per GPU, minute granularity
1× B300 (Blackwell Ultra)¥32.73¥32.73—
 已核实
4天前

GPU型号

B300 (Blackwell Ultra)B200H200H100 SXMA100 80GBA100 40GB

类似服务商

Together AIOpen-model inference API plus self-serve and reserved NVIDIA GPU clustersUSfalGenerative media platform with pay-per-use model APIs and serverless GPUsUSCirrascaleSan Diego AI cloud with NVIDIA, AMD, Qualcomm and Tenstorrent systems on term pricingUSHugging FaceAI model hub selling GPU Spaces, dedicated Inference Endpoints and routed inferenceUSFireworks AIFast inference and fine-tuning platform with per-second on-demand GPU deploymentsUSBasetenInference platform for dedicated model deployments and model APIs, billed per minuteUSGMI CloudNVIDIA Cloud Partner renting H100/H200/B200 and GB200 from its own data centersUSGroqInference neocloud built on its own LPU accelerators, serving models via GroqCloudUS