Baseten
CuratedActiveInference platform for dedicated model deployments and model APIs, billed per minute
From
—
GPU from
$0.848/GPU-hr
Locations
0
countries
Data centers
0
sites
Networks (ASN)
0
ASNs
Plans & prices
4
plans
Overview
Baseten deploys open and custom models (packaged with its Truss framework) on autoscaling dedicated GPUs billed by the minute, and sells hosted model APIs and training jobs. It runs a multi-cloud capacity pool and acqui-hired the Inferless team in 2026.
Plans & prices
GPU instances4
| Instance | Config | per GPU-hr | Total /hr | Spot | Locations | Source |
|---|---|---|---|---|---|---|
NVIDIA L4 — $0.01414/min | 1× L4 | $0.848 | $0.848 | — | Verified 3 days ago | |
NVIDIA A100 80GB — $0.06667/min per GPU | 1× A100 80GB | $4.00 | $4.00 | — | Verified 3 days ago | |
NVIDIA H100 80GB — $0.10833/min per GPU | 1× H100 SXM | $6.50 | $6.50 | — | Verified 3 days ago | |
NVIDIA B200 — $0.16633/min per GPU | 1× B200 | $9.98 | $9.98 | — | Verified 3 days ago |
GPU models
Similar providers
Together AIOpen-model inference API plus self-serve and reserved NVIDIA GPU clusters
falGenerative media platform with pay-per-use model APIs and serverless GPUs
CirrascaleSan Diego AI cloud with NVIDIA, AMD, Qualcomm and Tenstorrent systems on term pricing
Hugging FaceAI model hub selling GPU Spaces, dedicated Inference Endpoints and routed inference
DeepInfraLow-cost model inference API plus dedicated A100-to-B300 GPUs billed by the minute
Fireworks AIFast inference and fine-tuning platform with per-second on-demand GPU deployments
GMI CloudNVIDIA Cloud Partner renting H100/H200/B200 and GB200 from its own data centers
GroqInference neocloud built on its own LPU accelerators, serving models via GroqCloud