News
DealsCorvex agrees USD 103 million take-or-pay deal to perform AI inference with Mid-Atlantic GPUsSovereignNeysa scales AI infrastructure in India with AMD Instinct MI350X GPUs on TytanInferenceMicrosoft Foundry adds Baseten, DeepSeek AI inference (MSFT:NASDAQ)ClustersDataOne and Rowan University sign engineering co-op program agreement for DataOne's Vineland AI factoryClustersLook inside Cal Poly's $3 million AI Factory (Video)DealsOpenAI Taps AMD Chips for 457 MW of AI Capacity in Six-Year TensorWave DealClustersCal Poly launches an AI data center on campus. Take a look insideInferenceArista takes aim at the next AI network battleground: distributed inferenceDealsOpenAI Signs 457 MW AI Data Center Deal as AMD Expands Its Challenge to NvidiaClustersBehind Dell AI Factory鈥檚 NVIDIA & AMD Enterprise ExpansionDealsCorvex agrees USD 103 million take-or-pay deal to perform AI inference with Mid-Atlantic GPUsSovereignNeysa scales AI infrastructure in India with AMD Instinct MI350X GPUs on TytanInferenceMicrosoft Foundry adds Baseten, DeepSeek AI inference (MSFT:NASDAQ)ClustersDataOne and Rowan University sign engineering co-op program agreement for DataOne's Vineland AI factoryClustersLook inside Cal Poly's $3 million AI Factory (Video)DealsOpenAI Taps AMD Chips for 457 MW of AI Capacity in Six-Year TensorWave DealClustersCal Poly launches an AI data center on campus. Take a look insideInferenceArista takes aim at the next AI network battleground: distributed inferenceDealsOpenAI Signs 457 MW AI Data Center Deal as AMD Expands Its Challenge to NvidiaClustersBehind Dell AI Factory鈥檚 NVIDIA & AMD Enterprise Expansion
EveryNeocloud

Serverless GPUs

Pay per second, scale to zero. 41 providers on EveryNeocloud so far.

Serverless GPUs let customers run code on a GPU without choosing or managing a server. They upload a model or a function, the platform starts a GPU when a request comes in and bills by the second, and when no requests come the cost falls to zero. Modal, RunPod, Replicate and Baseten are known for it, and the big clouds and Cloudflare have added it.

How it works

The platform keeps a pool of GPUs and loads each customer's container when needed. The hard part is the cold start, the time to load a large model onto a GPU, which can take seconds or minutes. Platforms cut it by caching models, keeping some copies warm and loading weights in parallel. Billing per second suits uneven traffic, such as an app that is busy by day and quiet at night.

Who offers it

Google added GPUs to its Cloud Run service in 2025, and Microsoft offers serverless GPUs in Azure Container Apps. Cloudflare runs models on GPUs in its network through Workers AI, launched in 2023. Hugging Face lets users call many models without managing servers. For steady, heavy traffic, reserved servers usually cost less than serverless.

Famous serverless GPUs providers

Still to be written: Google Cloud Platform, Hugging Face.

Further reading

馃嚭馃嚫 United States and 2 moreGroq Chip designer and inference cloud built on its own Language Processing UnitChipmaker cloud 路 Groq LPU 路 2016 Gcore 馃嚤馃嚭 Luxembourg and 1 moreGcore Luxembourg edge AI, cloud, CDN and security provider with GPU clusters in EuropeNeocloud 路 Other Nvidia GPUs 路 2011 Amazon Bedrock 馃嚭馃嚫 United StatesAmazon Bedrock Serverless platform giving one API to many foundation modelsInference platform 路 2023 馃嚭馃嚫 United StatesCloudflare Edge network running Nvidia GPUs for AI inference via Workers AIInference platform 路 Other Nvidia GPUs 路 2009 Chutes WorldChutes Serverless, decentralised compute for running open-source AI models in productionInference platform Together AI 馃嚭馃嚫 United StatesTogether AI AI cloud running open models on demand, with GPU clusters and inference researchNeocloud 路 Nvidia Blackwell Crusoe 馃嚭馃嚫 United States and 3 moreCrusoe AI cloud and modular data centre operator that also builds its own power supplyNeocloud 路 Nvidia Blackwell Verda 馃嚝馃嚠 FinlandVerda European full-stack AI cloud offering GPU clusters, instances and model APIsNeocloud 路 Nvidia Blackwell Fal 馃嚭馃嚫 United StatesFal Serverless GPU platform for generative AI inferenceInference platform 路 Other Nvidia GPUs 路 2021 Novita AI 馃嚭馃嚫 United StatesNovita AI AI cloud platform offering model APIs and GPU instances for developers.Neocloud 路 Other Nvidia GPUs Modal 馃嚭馃嚫 United States and 1 moreModal Serverless cloud platform for AI development and inferenceDeveloper cloud 路 Other Nvidia GPUs Featherless AI 馃嚭馃嚫 United StatesFeatherless AI Serverless inference platform for open-source AI modelsInference platform 路 AMD Instinct 路 2023 Cerebrium 馃嚳馃嚘 South AfricaCerebrium Serverless GPU infrastructure for real-time AI workloadsInference platform 路 Nvidia Hopper PPIO 馃嚚馃嚦 ChinaPPIO Independent AI cloud for agent infrastructure and GPU computeNeocloud 路 Other Nvidia GPUs 路 2018 Fireworks AI 馃嚭馃嚫 United StatesFireworks AI Platform for running and training open AI modelsInference platform 路 Other Nvidia GPUs Runware 馃嚭馃嚫 United StatesRunware Serverless AI inference platform with custom hardwareInference platform 路 Other Nvidia GPUs 路 2023 Inferless 馃嚭馃嚫 United StatesInferless Serverless GPU inference platform for custom modelsInference platform 路 Other Nvidia GPUs Avian 馃嚭馃嚫 United StatesAvian Serverless and dedicated GPU inference for open-source modelsInference platform 路 Nvidia Blackwell FriendliAI 馃嚢馃嚪 South KoreaFriendliAI Accelerated generative AI inference serving platformInference platform 路 Other Nvidia GPUs Replicate WorldReplicate Run, fine-tune and deploy AI models through one APIInference platform GMI Cloud WorldGMI Cloud AI-native cloud for production inference, GPU clusters and agent runtimesNeocloud 路 Nvidia Hopper Parasail 馃嚭馃嚫 United StatesParasail Inference cloud for AI startups, billed by token.Inference platform 路 Other and custom chips Jarvislabs 馃嚠馃嚦 IndiaJarvislabs GPU cloud and inference platform based in IndiaNeocloud 路 Nvidia Hopper

Photo credits on this page

The small pictures above come from Wikimedia Commons under free licences. Some are cropped to fit.

The weekly digest

Every Monday: the provider of the day, new pages on EveryNeocloud, and the conferences and anniversaries of the week ahead.