Cerebrium
CuratedActivecerebrium.aiSince 2021
Real-time serverless GPU platform for voice, LLM and video inference
From
—
GPU from
$1.95/GPU-hr
Locations
0
countries
Data centers
0
sites
Networks (ASN)
0
ASNs
Plans & prices
5
plans
Overview
Cerebrium is a serverless AI infrastructure platform that deploys containerised models on GPUs from T4 to B200 with per-second billing, low cold starts and multi-region routing across several cloud providers, aimed at real-time voice and LLM applications.
Plans & prices
GPU instances5
| Instance | Config | per GPU-hr | Total /hr | Spot | Locations | Source |
|---|---|---|---|---|---|---|
NVIDIA L40S — $0.000542/s, GPU only | 1× L40S | $1.95 | $1.95 | — | Verified 4 days ago | |
NVIDIA A100 80GB — $0.000583/s, GPU only | 1× A100 80GB | $2.10 | $2.10 | — | Verified 4 days ago | |
NVIDIA H100 — $0.000944/s, GPU only | 1× H100 SXM | $3.40 | $3.40 | — | Verified 4 days ago | |
NVIDIA H200 — $0.001166/s, GPU only | 1× H200 | $4.20 | $4.20 | — | Verified 4 days ago | |
NVIDIA B200 — $0.00167/s, GPU only | 1× B200 | $6.01 | $6.01 | — | Verified 4 days ago |
GPU models
Similar providers
RunPodDeveloper GPU cloud with per-second Pods, serverless endpoints and community hosts
ModalPython-native serverless cloud with per-second GPUs from T4 to B300
falGenerative media platform with pay-per-use model APIs and serverless GPUs
FriendliAIInference platform with model APIs, per-second dedicated GPUs and bring-your-own-GPU
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
DeepInfraLow-cost model inference API plus dedicated A100-to-B300 GPUs billed by the minute
BasetenInference platform for dedicated model deployments and model APIs, billed per minute