Baseten runs its model-inference stack on Nebius AI Cloud GPU clusters in the United States, Finland and France. Nebius dates this regional deployment to September 2025. Baseten describes a custom text-to-video system running on Nebius capacity for production video generation.
The implementation uses modality-specific kernels, kernel fusion, request prioritization and topology-aware parallelism. Its infrastructure provides intelligent request routing, geographic load balancing, autoscaling and fast cold starts. Baseten also describes continuous batching, asynchronous compute, active-active reliability and multi-cloud capacity management. Baseten reports predictable P90/P99 latency, high utilization and stable uptime on Nebius capacity.
Nebius’s Q2 2025 shareholder letter also states that Baseten runs internal workloads on its infrastructure. The letter describes a completed platform integration that lets end users deploy through Baseten Cloud with Nebius as the underlying infrastructure.
Mike Bilodeau describes Baseten’s custom text-to-video system on Nebius. Its stack uses continuous batching and asynchronous compute, with active-active reliability and multi-cloud capacity management.
Baseten: AI video on Nebius6 Oct 2025 · Baseten · Web pageMike Bilodeau describes Baseten’s custom text-to-video system on Nebius. Its stack uses continuous batching and asynchronous compute, with active-active reliability and multi-cloud capacity management.
Nebius Baseten inference stack on Nebius
6 Oct 2025 · Nebius · Web page
Nebius states that Baseten has run on its GPU clusters in the US, Finland and France since September 2025. It describes production text-to-video inference using Baseten’s runtime and orchestration on Nebius AI Cloud.
Nebius Baseten inference stack on Nebius6 Oct 2025 · Nebius · Web pageNebius states that Baseten has run on its GPU clusters in the US, Finland and France since September 2025. It describes production text-to-video inference using Baseten’s runtime and orchestration on Nebius AI Cloud.
Nebius states that Baseten runs internal workloads on Nebius. Its Q2 integration also lets end users deploy through Baseten Cloud with Nebius as the underlying infrastructure.
Nebius%20-%20Letter%20to%20shareholders%20-%20Q2%202025.pdf?cache-buster=2025-08-26T16:52:55.017Z14 Oct 2026 · assets.nebius.com · PDFNebius states that Baseten runs internal workloads on Nebius. Its Q2 integration also lets end users deploy through Baseten Cloud with Nebius as the underlying infrastructure.
Nebius states that Baseten Cloud runs on Nebius in the USA, Finland and France. The companies jointly serve model-inference workloads through their integration.
#partnerships #aiinfrastructure #modelinference | Nebius14 Oct 2026 · www.linkedin.com · Web pageNebius states that Baseten Cloud runs on Nebius in the USA, Finland and France. The companies jointly serve model-inference workloads through their integration.
Baseten builds infrastructure and developer tools for deploying, running, and training AI models. Software and machine learning teams use its platform to serve language, speech, image, and embedding models in production. Its products include Dedicated Inference, ready-to-use Model APIs, managed Training Jobs, and the Loops training SDK, currently in early access. Truss packages custom models, while Chains orchestrates workflows across multiple models. Customers include OpenEvidence, Writer, and Zed. Deployments can run on Baseten’s cloud, in customers’ own clouds, or across both.
Documented financing · private company
Amount$1.5BSeries F
Valuation at announcementValuation$13B, basis unspecified$13B, basis unspecified
Reflection’s Beam became available through Baseten Model APIs and Dedicated Inference. The open-weight model has 501 billion parameters and a one-million-token context window for coding and agent workflows.
Meta’s Muse Spark Open became available through Baseten Model APIs and Dedicated Inference. The 816-billion-parameter model supports text, image, video and audio inputs with a one-million-token context window.
NVIDIA Nemotron 3.5 Super VL became available through Baseten Model APIs and Dedicated Inference. Developers can also customize the multimodal model through Baseten Training.
Baseten runs its model-inference stack on Nebius AI Cloud GPU clusters in the United States, Finland and France. Nebius dates this regional deployment to September 2025. Baseten describes a custom text-to-video system running on Nebius capacity for production video generation.
The implementation uses modality-specific kernels, kernel fusion, request prioritization and topology-aware parallelism. Its infrastructure provides intelligent request routing, geographic load balancing, autoscaling and fast cold starts. Baseten also describes continuous batching, asynchronous compute, active-active reliability and multi-cloud capacity management. Baseten reports predictable P90/P99 latency, high utilization and stable uptime on Nebius capacity.
Nebius’s Q2 2025 shareholder letter also states that Baseten runs internal workloads on its infrastructure. The letter describes a completed platform integration that lets end users deploy through Baseten Cloud with Nebius as the underlying infrastructure.
Mike Bilodeau describes Baseten’s custom text-to-video system on Nebius. Its stack uses continuous batching and asynchronous compute, with active-active reliability and multi-cloud capacity management.
Baseten: AI video on Nebius6 Oct 2025 · Baseten · Web pageMike Bilodeau describes Baseten’s custom text-to-video system on Nebius. Its stack uses continuous batching and asynchronous compute, with active-active reliability and multi-cloud capacity management.
Nebius Baseten inference stack on Nebius
6 Oct 2025 · Nebius · Web page
Nebius states that Baseten has run on its GPU clusters in the US, Finland and France since September 2025. It describes production text-to-video inference using Baseten’s runtime and orchestration on Nebius AI Cloud.
Nebius Baseten inference stack on Nebius6 Oct 2025 · Nebius · Web pageNebius states that Baseten has run on its GPU clusters in the US, Finland and France since September 2025. It describes production text-to-video inference using Baseten’s runtime and orchestration on Nebius AI Cloud.
Nebius states that Baseten runs internal workloads on Nebius. Its Q2 integration also lets end users deploy through Baseten Cloud with Nebius as the underlying infrastructure.
Nebius%20-%20Letter%20to%20shareholders%20-%20Q2%202025.pdf?cache-buster=2025-08-26T16:52:55.017Z14 Oct 2026 · assets.nebius.com · PDFNebius states that Baseten runs internal workloads on Nebius. Its Q2 integration also lets end users deploy through Baseten Cloud with Nebius as the underlying infrastructure.
Nebius states that Baseten Cloud runs on Nebius in the USA, Finland and France. The companies jointly serve model-inference workloads through their integration.
#partnerships #aiinfrastructure #modelinference | Nebius14 Oct 2026 · www.linkedin.com · Web pageNebius states that Baseten Cloud runs on Nebius in the USA, Finland and France. The companies jointly serve model-inference workloads through their integration.
Baseten builds infrastructure and developer tools for deploying, running, and training AI models. Software and machine learning teams use its platform to serve language, speech, image, and embedding models in production. Its products include Dedicated Inference, ready-to-use Model APIs, managed Training Jobs, and the Loops training SDK, currently in early access. Truss packages custom models, while Chains orchestrates workflows across multiple models. Customers include OpenEvidence, Writer, and Zed. Deployments can run on Baseten’s cloud, in customers’ own clouds, or across both.
Documented financing · private company
Amount$1.5BSeries F
Valuation at announcementValuation$13B, basis unspecified$13B, basis unspecified
Reflection’s Beam became available through Baseten Model APIs and Dedicated Inference. The open-weight model has 501 billion parameters and a one-million-token context window for coding and agent workflows.
Meta’s Muse Spark Open became available through Baseten Model APIs and Dedicated Inference. The 816-billion-parameter model supports text, image, video and audio inputs with a one-million-token context window.
NVIDIA Nemotron 3.5 Super VL became available through Baseten Model APIs and Dedicated Inference. Developers can also customize the multimodal model through Baseten Training.
