Skip to content
SPECIFICTION
Get listed

Baseten

baseten.co

Free plan WebAPISelf-hosted
Visit baseten.co
Spec score 8.1 #1 of 25 in Model Hosting

Spec sheet

Product
Baseten provides an inference platform for serving open-source, custom, and fine-tuned AI models in production.Read 29 Sep 2026 · baseten.co
Integrations
Baseten’s hosted web search tools launched with Exa, Keenable, Parallel, and You.com.Read 29 Sep 2026 · baseten.co
Security
Baseten states it is SOC 2 Type II certified and HIPAA compliant; its security practices page also describes GDPR support and available data processing addendum.Read 29 Sep 2026 · baseten.co
Support
Support varies by plan and includes email, in-app chat, Slack, Zoom, and dedicated forward-deployed engineering support.Read 29 Sep 2026 · baseten.co
Headquarters
San Francisco, California, United StatesRead 23 Sep 2026 · baseten.co
Founded
2019Read 23 Sep 2026 · baseten.co
Company history
Baseten says it was founded in 2019 by engineers who set out to solve the challenges of deploying machine learning systems to production.Read 29 Sep 2026 · baseten.co
Data handling
Baseten Cloud says it does not store model inputs or outputs.Read 29 Sep 2026 · baseten.co
Free credits
The pricing FAQ says new accounts come with credits for experimenting with the UI and deployments for free.Read 29 Sep 2026 · baseten.co
Hosting
Baseten offers managed cloud, self-hosted, and hybrid deployment options, including deployments in a customer’s VPC.Read 29 Sep 2026 · baseten.co
Model packaging
Customers can deploy any model using Truss, Baseten’s open-source standard for packaging and serving models built in any framework.Read 29 Sep 2026 · baseten.co
Pre-optimized models
Its Model APIs provide access to pre-optimized models running on the Baseten Inference Stack.Read 29 Sep 2026 · baseten.co
Training
Baseten offers training infrastructure and says models trained with its Loops SDK can be deployed to production inference on the same stack.Read 29 Sep 2026 · baseten.co
Usage charges
Dedicated deployment compute is billed by usage down to the minute, and the pricing FAQ says idle time is not charged.Read 29 Sep 2026 · baseten.co
Workloads
The platform describes support for image generation, transcription, text-to-speech, LLM inference, embeddings, and compound AI.Read 29 Sep 2026 · baseten.co

Plans and prices

Basic Free $0 per month, pay as you go Dedicated deployments · Model APIs · Training · Fast cold starts · Email and in-app chat support Read 29 Sep 2026 · baseten.co
Enterprise Priced on request Volume discounts available; get a quote Everything in Pro · Custom SLAs · Self-host deployments · On-demand flex compute · Data residency control · Advanced security and compliance · Custom global regions · Advanced RBAC with Teams Read 29 Sep 2026 · baseten.co
Pro Priced on request Volume discounts available; get a quote Everything in Basic · Priority access to high-demand GPUs · Dedicated compute · Higher Model API rate limits · Hands-on engineering expertise · Dedicated Slack and Zoom support Read 29 Sep 2026 · baseten.co

Every Baseten plan and price →

Where Specifiction places it

Alternatives to BasetenAll alternatives →