C

CoreWeave Dedicated Inference

API service

by CoreWeave

Managed inference for a customer's own or open-source model weights on GPU classes the customer picks, served through OpenAI-compatible vLLM and SGLang endpoints while CoreWeave runs the cluster, routing and scaling, billed per GPU-hour.

Find alternatives to CoreWeave Dedicated Inference

What it does

• Model inference

Sources

Pricing

Official documentation · 18 Oct 2026

"Per GPU-hour billing against your chosen GPU class and capacity model. No egress fees, no ingress fees, no service markup."; "Pay-per-GPU-hour".

Description

Official documentation · 18 Oct 2026

"Deploy custom weights on explicitly chosen GPUs. CoreWeave operates routing, scaling, and lifecycle."; "vLLM and SGLang runtimes with OpenAI-compatible endpoints out of the box."; "Single-node or distributed multi-node serving, billed per GPU-hour."

What it does

Official documentation · 18 Oct 2026

"Teams deploying domain-specific or fine-tuned models who need custom weights support, GPU selection, and a path from training to production".

Sold within

Not found · 18 Oct 2026

"INFERENCE IS PART OF COREWEAVE FORGE"; the page states no plan that includes Dedicated Inference and sells it through "Contact sales".

Name

Official documentation · 18 Oct 2026

"Dedicated Inference from CoreWeave".

URL

Official documentation · 18 Oct 2026

The product's own page, titled "Dedicated Inference"; the Forge menu describes it as "Your weights on GPUs you choose, managed for you".

Deployment

Official documentation · 18 Oct 2026

"Organizations that need single-tenant GPU nodes, Availability Zone placement for data sovereignty"; "A tenant-isolated gateway runs authentication, load balancing, and request routing across replicas."

Interfaces

Official documentation · 18 Oct 2026

"vLLM and SGLang runtimes with OpenAI-compatible endpoints out of the box."

Intended for

Official documentation · 18 Oct 2026

"AI TEAMS", "ENTERPRISE" and "PLATFORM TEAMS" are the three audiences the page names.

Also from CoreWeave

• CoreWeave AI Cloud Infrastructure service

  GPU cloud renting NVIDIA accelerators by the hour, with managed Kubernetes, storage and networking for training and inference.

• Mission Control Platform

  Operating layer for CoreWeave Cloud unifying security (IAM, compliance logging), fleet/node lifecycle automation with expert support, and observability (metrics, logs, telemetry), including an AI agent that answers questions about GPU performance and cluster health.

• CoreWeave Sandboxes Infrastructure service

  Managed sandbox compute environments for AI development, billed as an add-on that varies with the buyer's base Weights & Biases plan tier ($10/mo on Free, $25/mo on Pro).

• CoreWeave ARIA AI agent

  AI research agent built into the Weights & Biases platform that analyzes experiment data and production traces, forms hypotheses, designs and runs experiments, and generates dashboards and reports.

• CoreWeave Forge Platform

  CoreWeave Forge provides a development environment for running, observing, improving, and evaluating models and agents.

• CoreWeave Kubernetes Service Infrastructure service

  CoreWeave Kubernetes Service provides managed Kubernetes clusters for building, training, and deploying AI applications.

• CoreWeave SUNK Infrastructure service

  CoreWeave SUNK runs Slurm jobs and Kubernetes workloads on shared compute for AI training.

• SUNK Anywhere Infrastructure service

  SUNK Anywhere licenses SUNK Standard for running Slurm on Kubernetes clusters operated outside CoreWeave.

• CoreWeave Agent Lens Application

  Observability for production AI agents that groups failures across millions of traces, lets teams tune LLM judges and turn each failure into a test case, and checks candidate fixes against real cases before they ship; in preview inside CoreWeave Forge.

• CoreWeave Model Distillation Platform

  Managed post-training workflow that trains a smaller open-weight model on examples from a production task with Serverless supervised fine-tuning, scores it against the model already in use on held-out traffic, and moves traffic over gradually; in preview inside CoreWeave Forge.

• CoreWeave Notebooks Developer tool

  Reactive Python and SQL notebooks that open inside CoreWeave Forge already connected to a project's experiment runs, for analysing training runs and model and agent evaluation results next to the data.

Open CoreWeave in the directory

Something wrong here? Send a correction — quote this product id: coreweave-dedicated-inference.