Inference Endpoints

What it does

• Training ML models at scale
• Fine-tuning AI models
• Serving ML inference
• Multi-node GPU clusters

Category

Model hosting and inference

Users

AI/ML teams, Academic research, Enterprises with AI workloads, NLP and foundation model teams and 2 more

Public API

Not offered

Not yet disclosed: deployment options, platforms, languages and support channels.

Pricing

• Free plan$0

Prices as published by VESSL AI, checked Oct 2026.

Security and compliance

As reported by VESSL AI. Ask for audit reports before you buy.

• SOC 2 Type IICompliant

Reviews

• 

  Moonshine

  Deploys AI models as callable endpoints on serverless GPUs.

• 

  Inference

  by Beam

  Deploy high-performance inference endpoints for serving custom models on GPU or CPU.

• 

  Red Hat AI Inference

  by Red Hat

  Optimize model performance with an integrated stack for fast, consistent, and cost-effective inference at scale.

• 

  Model Serving

  by INTELLITHING

  Solution for serving models via production-grade APIs with access management and monitoring; listed as a core platform capability.

• 

  Cumulus — Production-Grade Inference Platform

  by Cumulus Labs

  Unified inference platform with eight subsystems: Gateway, Router, Cache, Observability, Evaluation, Fine-tune, Custom Hosting, and the Ion inference engine.

• 

  Dedicated Model Inference

  by Together AI

  Deploy models on dedicated infrastructure.