Baseten pricing

Baseten is an inference platform for running open-source, custom and fine-tuned AI models, with pre-optimized Model APIs, dedicated GPU deployments and training.

AI API platformsPriced per minuteSelf-serve + sales

Visit BasetenPrices checked Oct 29, 2026

How much does Baseten cost?

Usage price from $1.40/minute

Free plan: Not stated
Free trial: New accounts come with free credits; duration not stated
Usage price: $1.40/minute
Enterprise: Contact sales

Read from www.baseten.co/pricing/ on Oct 29, 2026. Price changed? Tell usSee the line each price came from

In your favor

Free trial. New accounts come with free credits; duration not stated

How you buy and get started

Self-serve + salesButtons on their site: Get started, Start building, Get a quote, Talk to an engineer

Sign up: Self-serve signup
Setup: Not stated
When sales steps in: Pro and Enterprise are by quote
Support: Email and in-app chat on Basic
Support: Dedicated Slack and Zoom on Pro

What Baseten does

Baseten offers pay-per-token Model APIs for hosted open models and per-minute dedicated GPU and CPU deployments for custom models, plus a training product. It can run in Baseten's cloud, in a customer's VPC (self-hosted) or hybrid.

Good for: Teams that need high-performance, production-scale inference for open-source, custom or fine-tuned models, including regulated workloads that need SOC 2 or HIPAA.
Channels: Baseten Cloud, Self-hosted (your VPC), Hybrid
Main product: Baseten Inference Stack: Model APIs, Dedicated Deployments and Training
Also includes: Dedicated deployments, Model APIs, Training, Fast cold starts, SOC 2 Type II and HIPAA compliant, Email and in-app chat support
Public API: Yes
MCP server: Not stated

Pay-per-token pricingPrice per 1M tokens
Multiple models availableInstant access to pre-optimized models running on the Baseten Inference Stack.
Fine-tuning supportServe open-source, custom, and fine-tuned AI models on infra purpose-built for high-performance inference at m
Streaming responsesWe built real-time audio streaming to power AI phone calls, voice agents, translation, and more with the lowes
Tool and function callingNot stated
SOC 2 complianceWe are SOC-2 Type II certified and HIPAA compliant across all hosting options
No training on your dataNot stated
Discounted batch processingNot stated

The same 8 checks appear on every tool in AI API platforms. Each tick quotes the vendor's own site.

Security and your data

Question	Their answer	Where it says so
Trains AI on your data?	Not stated
HIPAA (signs a BAA)	available	"Baseten's standard BAA is available at <https://www.baseten.co/baa>"terms
SOC 2	SOC 2 Type II	"Yes, Baseten is SOC 2 Type II certified and HIPAA compliant."pricing
GDPR	listed	"GDPR"security
CCPA	compliant	"CCPA"security
PCI	PCI DSS SAQ D	"PCI DSS - SAQ D"security
ISO 27001	ISO 27001:2022	"ISO 27001:2022"security
Single sign-on	supported	"With RBAC and fine-grained team-level access controls, SSO, integration support across detailed logging, custom metrics, and tracing"enterprise
Trust center	https://trust.baseten.co	"Baseten's Trust Center"security

Security answers are the vendor's own claims, quoted. We don't audit them.

Every plan

Plan	Monthly	Billed yearly	Included	Over the allowance	Where it says so
Basicper month, pay as you go	$0	–	–	–	"$0 per month, pay as you go"
Model APIs: GLM-5.3 (input)per 1M input tokens	$1.40per minute	–	–	–	"$1.40"
Dedicated Deployments: H100 (80 GiB VRAM)per minute	$0.11per minute	–	–	–	"$0.10833"
Dedicated Deployments: A100 (80 GiB VRAM)per minute	$0.07per minute	–	–	–	"$0.06667"
Dedicated Deployments: T4 (16 GiB VM)per minute	$0.01per minute	–	–	–	"$0.01052"
Pro	Quote	–	–	–	"Volume discounts available"
Enterprise	Quote	–	–	–	"Contact our sales team to discuss pricing based on your specific needs"