Inceptron
Swedish AI inference platform offering model APIs, inference optimization and dedicated deployments. · Infrastructure
How they use Nebius AI Cloud
Inceptron provides an AI inference platform for deploying, optimizing and scaling models. It offers model APIs, custom checkpoint deployment and dedicated deployments. Its proprietary compiler optimizes models for target hardware through graph fusion, kernel tuning and memory planning.
Kontinent reports that Inceptron uses Nebius infrastructure hosting and compute in Finland and France for EU-region workloads. Dentro’s European infrastructure directory describes Inceptron as running its own inference engine and using Nebius servers alongside other infrastructure.
Sources
2 sourcesDentro’s European infrastructure directory
19 Oct 2026 · GitHub · Web page
Dentro reports that Inceptron serves open-source models with its own inference engine and uses Nebius servers alongside other infrastructure.
Open original sourceCompany context
inceptron.ioInceptron is an AI inference platform operated by Inceptron AB in Lund, Sweden. It helps developers and machine-learning teams deploy, optimize and scale open-source or fine-tuned models in production. Its main offerings include serverless model APIs, inference optimization software and dedicated GPU deployments for workloads requiring more control or capacity. Customers can prototype through hosted endpoints and move to dedicated infrastructure as usage grows. The platform also supports EU-hosted processing for teams with European data residency requirements.
Documented financing · private company
Recent updates
2 updatesHedy selects Inceptron for EU AI processing
Inceptron announced that Hedy’s EU cloud AI processing now runs on its infrastructure. Hedy’s EU region generates approximately 6 billion tokens monthly, with EU-only processing covered by the companies’ data processing agreement.
InceptronInceptron announces full model catalogue availability through Opper AI
Inceptron announced that Opper users can access all its hosted models through the Opper API, including GLM 5.3, GLM 5.3 Flash and DeepSeek V4 Flash. The September announcement broadens the catalogue beyond the MiniMax M2.5 integration previously announced by Opper.
Inceptron