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 TytanSovereignNeysa Deploys AMD GPU Cluster in Mumbai for AI Training and InferenceInferenceMicrosoft Foundry adds Baseten, DeepSeek AI inference (MSFT:NASDAQ)ClustersWhat Does Hewlett Packard Enterprise (HPE) Gaining A Top 14 AI Supercomputer Mean?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 inferenceDealsCorvex 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 TytanSovereignNeysa Deploys AMD GPU Cluster in Mumbai for AI Training and InferenceInferenceMicrosoft Foundry adds Baseten, DeepSeek AI inference (MSFT:NASDAQ)ClustersWhat Does Hewlett Packard Enterprise (HPE) Gaining A Top 14 AI Supercomputer Mean?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 inference
EveryNeocloud

Inference platforms

Fireworks, Baseten, Replicate, Modal and the clouds that serve models by the token. 34 providers on EveryNeocloud so far.

An inference platform runs trained AI models for customers and charges for the work, usually by the token, the small chunk of text a language model reads or writes. Customers send a request to an API and get an answer back, without renting a whole GPU. Fireworks, Baseten, Together AI, Replicate and Modal are known examples, along with the chip companies Groq, Cerebras and SambaNova.

Training versus inference

Training a model is a long job that keeps thousands of GPUs busy for weeks. Inference is the opposite: millions of short requests that must be answered in a fraction of a second. Inference platforms pack many customers onto shared GPUs, batch requests together, cache repeated text and use tricks such as quantisation, storing numbers with fewer bits, to cut cost and delay. As AI tools spread, inference has become a larger share of all AI computing.

How they sell

Most publish prices per million input and output tokens for popular open models such as Llama, Qwen, DeepSeek and Mistral, and offer dedicated deployments for larger customers. Many rent their GPUs from neoclouds rather than owning them. The hyperscalers compete with services such as Amazon Bedrock, and routers such as OpenRouter send each request to whichever provider is cheapest or fastest.

Famous inference platform providers

Still to be written: Hugging Face.

Further reading

馃嚭馃嚫 United StatesSpaceX Super Intelligence Musk's AI company behind Grok and the Colossus data centres, now part of SpaceX.Neocloud 路 Nvidia Hopper 路 2023 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 馃嚭馃嚫 United StatesCloudflare Edge network running Nvidia GPUs for AI inference via Workers AIInference platform 路 Other Nvidia GPUs 路 2009 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 DeepInfra 馃嚭馃嚫 United StatesDeepInfra Inference cloud for open-source AI modelsInference platform 路 Nvidia Blackwell 路 2022 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 Saturn Cloud 馃嚭馃嚫 United StatesSaturn Cloud Managed inference platform for open AI models on dedicated GPUsInference platform 路 Other Nvidia GPUs Livepeer WorldLivepeer Open network for AI video inference workloadsMarketplace 路 Other Nvidia GPUs Inferless 馃嚭馃嚫 United StatesInferless Serverless GPU inference platform for custom modelsInference platform 路 Other Nvidia GPUs FriendliAI 馃嚢馃嚪 South KoreaFriendliAI Accelerated generative AI inference serving platformInference platform 路 Other Nvidia GPUs Simplismart 馃嚠馃嚦 IndiaSimplismart AI inference platform for custom model deployment and scalingInference platform 路 Nvidia Blackwell Neysa 馃嚠馃嚦 IndiaNeysa GPU cloud and AI platform for enterprises in IndiaNeocloud 路 Other Nvidia GPUs 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.