DeepInfra
CuratedActiveLow-cost model inference API plus dedicated A100-to-B300 GPUs billed by the minute
From
—
GPU from
$0.890/GPU-hr
Locations
0
countries
Data centers
0
sites
Networks (ASN)
0
ASNs
Plans & prices
5
plans
Overview
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.
Plans & prices
GPU instances5
| Instance | Config | per GPU-hr | Total /hr | Spot | Locations | Source |
|---|---|---|---|---|---|---|
Dedicated A100 80GB for custom LLMs — per GPU, minute granularity | 1× A100 80GB | $0.890 | $0.890 | — | Verified 3 days ago | |
Dedicated H100 for custom LLMs — per GPU, minute granularity | 1× H100 SXM | $2.20 | $2.20 | — | Verified 3 days ago | |
Dedicated H200 for custom LLMs — per GPU, minute granularity | 1× H200 | $2.69 | $2.69 | — | Verified 3 days ago | |
Dedicated B200 for custom LLMs — per GPU, minute granularity | 1× B200 | $3.69 | $3.69 | — | Verified 3 days ago | |
Dedicated B300 for custom LLMs — per GPU, minute granularity | 1× B300 (Blackwell Ultra) | $4.89 | $4.89 | — | 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
Fireworks AIFast inference and fine-tuning platform with per-second on-demand GPU deployments
BasetenInference platform for dedicated model deployments and model APIs, billed per minute
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