Baseten
Open siteStreamline AI deployment and scaling with robust, developer-friendly tools.
Baseten Information
What is Baseten?
Baseten is a platform that simplifies the deployment and management of AI models, offering features like autoscaling, performance optimizations, and compliance certifications. It supports various AI applications such as LLM inference, image generation, and audio transcription, and provides tools for building compound AI systems and managing model deployments.
Baseten Core Features
- Fast and scalable model inference
- Open-source model packaging with Truss
- Autoscaling infrastructure
- Global observability
- Enterprise-grade security and compliance
- Multi-cloud, multi-cluster support
- Customizable deployments
Baseten Pricing
basic
$0 per month, pay per minute of compute/month
- Best-in-class autoscaling
- Fast cold starts
- Up to 5 replicas per model
- Model observability & logging
- SOC 2 Type II & HIPAA compliant
- Email & in-app chat support
pro
Custom/month
- Everything in Basic plus:
- Unlimited number of replicas per model
- Volume discounts on compute
- Bring your whole team
- Priority access to high demand infrastructure including A100s and H100s
- Dedicated support on Slack and Zoom
enterprise
Custom/month
- Everything in Pro plus:
- Dedicated SLAs
- Advanced security and compliance
- Custom model management
- Early roadmap previews
- Custom regions
