Fireworks AI

已审核运营中
fireworks.aiUS美国成立 2022

Fast inference and fine-tuning platform with per-second on-demand GPU deployments

推理无服务器
访问官网 价格
起价
—
GPU起价
¥53.54/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

Fireworks AI, founded in 2022 by former PyTorch engineers at Meta, serves open models through a serverless token API and lets customers run on-demand deployments on dedicated GPUs (H100 to GB300) billed per GPU-second, plus fine-tuning and training APIs.

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
On-demand deployment, H200 141GB — per GPU, billed per second
1× H200¥53.54¥53.54—
 已核实
3天前
On-demand deployment, H100 80GB — per GPU, billed per second
1× H100 SXM¥53.54¥53.54—
 已核实
3天前
On-demand deployment, B200 180GB — per GPU, billed per second
1× B200¥87.01¥87.01—
 已核实
3天前
On-demand deployment, B300 288GB — per GPU, billed per second
1× B300 (Blackwell Ultra)¥100¥100—
 已核实
3天前
On-demand deployment, GB300 288GB — per GPU, billed per second
1× GB300 (Blackwell Ultra)¥134¥134—
 已核实
3天前

GPU型号

GB300 (Blackwell Ultra)B300 (Blackwell Ultra)B200H200H100 SXM

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 inferenceUSDeepInfraLow-cost model inference API plus dedicated A100-to-B300 GPUs billed by the minuteUSBasetenInference 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