Baseten Multi-cloud Capacity Management
Pools GPU capacity from 20+ clouds and regions as one resource for a customer's model replicas, with SLA-aware autoscaling, intelligent request routing and active-active failover.
Find alternatives to Baseten Multi-cloud Capacity Management
What it does
- Model inference
Sources
- Pricing
-
Official documentation · 18 Oct 2026
The page and the pricing page state no MCM price; the pricing page lists Dedicated Deployments, Model APIs and Training only.
- Description
-
Official documentation · 18 Oct 2026
"Use 20+ clouds as one GPU pool"; "Dynamically route and scale model replicas across clouds".
- What it does
-
Official documentation · 18 Oct 2026
"powering low latency with 99.99% uptime"; "SLA-aware autoscaling".
- Sold within
-
Read the MCM page and the pricing page: the product page says it runs "in our cloud or yours" but no page states which plan includes it or whether it is an add-on.
- Name
-
Official documentation · 18 Oct 2026
"Multi-cloud Capacity Management | Baseten"; "We built multi-cloud capacity management (MCM)".
- URL
-
Official documentation · 18 Oct 2026
The product page under Products > Multi-cloud.
- Deployment
-
Official documentation · 18 Oct 2026
"Run in our cloud, your cloud, or a combination of both."
- Intended for
-
Official documentation · 18 Oct 2026
"Mission-critical workloads need MCM"; data residency and sovereignty requirements.
Also from Baseten
-
Baseten Platform
Deploys and serves machine-learning models as production endpoints on managed GPU infrastructure.
-
Baseten Model APIs Model API
Pre-optimised hosted endpoints for open-source frontier models, called without deploying or managing a deployment first.
-
Baseten Training Platform
Trains and fine-tunes models on managed GPUs: Training Jobs (generally available, existing scripts) and Loops (early access, reinforcement learning through the Loops SDK), deploying the result onto Baseten's inference stack.
-
Baseten Frontier Gateway API service
Production-grade API launch platform for model labs: takes a lab's model from research to a reliable, scalable, white-labelled API in days, distinct from Baseten's Distribution Platform (model marketplace listing).
-
Baseten Inference Runtime Infrastructure service
Named inference runtime (automatic TensorRT/SGLang/vLLM builds, speculative decoding, custom kernel fusion, KV-cache optimisation) that underlies Baseten's Dedicated Inference, Model APIs and Training products.
-
Baseten Dedicated Inference Infrastructure service
Dedicated model deployments on the Baseten Inference Stack: autoscale across clouds, run in Baseten's cloud or the customer's, and pay for GPU or CPU compute by the minute.
Something wrong here? Send a correction — quote this product id: baseten-multi-cloud-capacity-management.