b stack radar
BentoML logo

BentoML Pricing

Every BentoML plan with its monthly and annual price, what it costs for common team sizes, and a calculator to estimate your own monthly cost before you buy.

Compare BentoML alternatives by priceRead our BentoML reviewCompare AI Software pricing

Plans and prices

PlanMonthly billingAnnual billing (per month)Per user or flatUsersFree tier
Open Source (Self-Hosted)FreeFree—No limit listedYes
Bento Cloud / Modular Cloud (usage-based)Contact salesContact sales—No limit listedNo
Bring Your Own CloudContact salesContact sales—No limit listedNo
EnterpriseContact salesContact sales—No limit listedNo

Prices last updated November 2026.

What each BentoML plan includes

Open Source (Self-Hosted)

  • Community support
  • Self-managed infrastructure
  • Apache 2.0 BentoML framework

Bento Cloud / Modular Cloud (usage-based)

  • Managed GPU endpoints
  • Autoscaling and scale-to-zero
  • Observability and usage metrics
  • Shared endpoints billed per token, dedicated endpoints billed per GPU minute

Bring Your Own Cloud

  • Standard and custom SLAs
  • Runs in your VPC or on-premises
  • Billed per minute of reserved GPU capacity

Enterprise

  • Custom SLAs
  • Custom contract
  • Multi-vendor GPUs
  • Forward-deployed engineers

What BentoML costs by team size

Team size1 user5 users10 users25 users50 users
Monthly costFreeOpen Source (Self-Hosted)FreeOpen Source (Self-Hosted)FreeOpen Source (Self-Hosted)FreeOpen Source (Self-Hosted)FreeOpen Source (Self-Hosted)

The plan that fits each team size, billed monthly, before add-ons and usage charges.

BentoML Pricing Calculator

Estimate your team's real monthly and annual cost based on seats, billing cycle, and add-ons.

Billing cycle

Cost breakdown

Total monthly costFree
Per year on annual billingFree
Cost per userFree/mo

Estimated from the vendor's published prices, last updated November 2026. Actual costs may vary based on negotiated contracts. How we collect prices

Ready to try BentoML?

Use this estimate to align with your team, then start a trial or subscription.

Visit BentoML

Better value alternatives

See what similar tools would cost for the same team size.

BentoML pricing FAQs

Modular's pricing page states SOC 2 Type 2 certification across its self-hosted, hosted and BYOC offerings.

Bentoml.com links to Modular's pricing page. That page shows per-token rates for shared endpoints, but custom or committed GPU pricing requires contacting sales.

Yes, BentoML has a free plan: Open Source (Self-Hosted).

BentoML's Open Source (Self-Hosted) plan includes Community support, Self-managed infrastructure and Apache 2.0 BentoML framework.

BentoML is free for 10 users on its Open Source (Self-Hosted) plan.