Skip to content

Inference APIs

Filter thousands of providers instantly. Everything happens in your browser.

29 providers
Nebius2004Amsterdam-based AI cloud with GB300/B300/H200 capacity and Token Factory inference$1.55/GPU-hr
immers.cloud2018Moscow GPU cloud with immersion-cooled servers and per-second billing$0.436/GPU-hr
Denvr Dataworks2007Canadian AI cloud with sovereign GPU compute in Canada and the US$1.10/GPU-hr
Cloud.ru2019Sber's cloud provider (ex-SberCloud) with Evolution IaaS/PaaS and GPU rental$3.58/GPU-hr
Intelion Cloud2024Moscow GPU cloud with per-second billing, H200/H100 SXM and 48GB RTX 4090 cards$0.597/GPU-hr
Together AI2022Open-model inference API plus self-serve and reserved NVIDIA GPU clusters$3.99/GPU-hr
fal2021Generative media platform with pay-per-use model APIs and serverless GPUs$4.00/GPU-hr
FriendliAI2021Inference platform with model APIs, per-second dedicated GPUs and bring-your-own-GPU$4.00/GPU-hr
Cirrascale2010San Diego AI cloud with NVIDIA, AMD, Qualcomm and Tenstorrent systems on term pricing$3.85/GPU-hr
Hugging Face2016AI model hub selling GPU Spaces, dedicated Inference Endpoints and routed inference$0.800/GPU-hr
Hyperbolic2021Open-access AI cloud with on-demand H100/H200/B200 and reserved clusters$1.29/GPU-hr
DeepInfra2013Low-cost model inference API plus dedicated A100-to-B300 GPUs billed by the minute$0.890/GPU-hr
Fireworks AI2022Fast inference and fine-tuning platform with per-second on-demand GPU deployments$8.00/GPU-hr
Baseten2019Inference platform for dedicated model deployments and model APIs, billed per minute$0.848/GPU-hr
GMI Cloud2024NVIDIA Cloud Partner renting H100/H200/B200 and GB200 from its own data centers$2.60/GPU-hr
Groq2016Inference neocloud built on its own LPU accelerators, serving models via GroqCloud—
NetMind2023Model APIs plus on-demand H100/A100/RTX 4090 GPUs from a distributed fleet—
Novita AI2023Model APIs plus on-demand, spot and serverless GPU instances and bare metal—
SiliconFlow2003Chinese AI inference platform serving open models with fine-tuning and reserved GPUs—
Bitdeer AI2024Singapore AI cloud from Bitdeer with GB300/GB200 NVL72 and serverless models—
Parasail2018AI deployment network for serverless, dedicated and batch inference across GPU suppliers—
Theta EdgeCloud2024Theta Labs' hybrid cloud-edge GPU platform for compute, inference and AI agents—
Nscale2024Vertically integrated AI cloud with hydro-powered data centers in Norway and the UK—
Cerebras2021Wafer-scale chipmaker running one of the fastest LLM inference clouds—
Chutes2024Open-source, decentralized serverless platform for running open models at scale—
SambaNova2017Dataflow-chip company serving fast open-model inference through SambaCloud—
Replicate2019Run and deploy open models through an API, billed per second; now part of Cloudflare$0.810/GPU-hr
Lepton AI2023AI cloud platform acquired by NVIDIA and relaunched as DGX Cloud Lepton—
OctoAI2016Model-serving platform (formerly OctoML) acquired by NVIDIA and shut down in 2024—
Loading index…