BentoML
bentoml.com
Framework and platform for serving AI models.
Quick Information
- Category:
- MLOps & Infrastructure
- Pricing:
- Freemium
- Platforms:
- Python, Cloud, Self-hosted
- Free Plan:
- Yes
- API Available:
- Yes
- Last Verified:
- October 2026
What Is BentoML?
BentoML is a framework and platform for serving AI models, with BentoCloud as the managed service. The framework is open source under Apache 2.0, and Modular, which acquired BentoML in February 2026, said it will remain Apache 2.0. BentoCloud is a separate, paid, usage-based service and the pricing sources conflict. A third-party aggregator lists three tiers as of June 2026, from bentoml.com/pricing: a free Starter tier with pay-as-you-go usage, Pro at $1,000 a month plus usage, and custom Enterprise with self-host or BYOC options, with rates such as CPU at $0.00001322 a second, NVIDIA T4 at $0.00014198 a second (about $0.51 an hour), L4 about $0.80 an hour and H100 about $2.65 an hour. A Spheron comparison instead says BentoCloud pricing is not publicly listed and estimates H100 at about $4.00 an hour, which it describes as an industry-benchmark estimate, not a published rate.
Ownership has moved again: per a usagepricing.com summary, Qualcomm closed its acquisition of Modular on July 29, 2026, and no BentoCloud pricing or packaging change has been disclosed as of that writing. Most of the 2026 pricing details come from aggregator sites rather than BentoML's own pricing page, and I could not verify them against bentoml.com/pricing, so check it before relying on specific numbers. Self-hosting the framework costs only your own infrastructure.
BentoML suits ML engineers who want to package models and LLM apps into production APIs with minimal boilerplate. Compare KServe, Ray and Hugging Face. Browse the MLOps & Infrastructure tools directory for more.
What Can You Use BentoML For?
Model inference APIs
Serve models.
LLM apps and pipelines
Multi-model.
BentoML Features
- Modular ownership — Acquired February 2026.
- Qualcomm acquired Modular — July 29, 2026 per one summary.
- Per-second compute billing — BentoCloud.
Who Is BentoML For?
- ML engineers — Simple serving.
- AI startups — Pay-as-you-go cloud.
BentoML Pros & Limitations
What We Like
- Open-source Apache 2.0
- Per-second billing
- Self-host or cloud
Limitations
- Pricing from aggregators
- Ownership changed twice in 2026
- Pro price disputed
BentoML Pricing
| Plan | Price | Main Features |
|---|---|---|
| BentoML framework | Free (Apache 2.0) | Self-hosted; Modular says it stays Apache 2.0 |
| BentoCloud Starter | Free plus pay-as-you-go usage | Per one aggregator |
| BentoCloud Pro | $1,000/month plus usage | Per one aggregator; Spheron says not publicly listed |
| Usage rates (aggregator) | T4 about $0.51/hour; L4 about $0.80; H100 about $2.65 | Spheron estimates H100 near $4.00 |
| Enterprise | Custom | Self-host or BYOC |
Pricing was last verified October 2026. Check the official website for the latest pricing.
AI Listing Jungle Ranking
- Global Rank:
- #864
- Overall Score:
- 48.4/100
- Monthly Users:
- –
- Rank Change:
- ▲ 685
This ranking reflects AI Listing Jungle's own independent scoring methodology and is not an endorsement by BentoML or its company. How Our Rankings Work
Frequently Asked Questions
Is BentoML free?
The framework is free under Apache 2.0.
How much is BentoCloud Pro?
Reportedly $1,000 a month plus usage.
Who owns BentoML?
Modular, acquired in February 2026; Qualcomm reportedly acquired Modular in July 2026.
Will it stay open source?
Modular says Apache 2.0 continues.
Our Take
BentoML is a clean way to serve models.
Confirm BentoCloud pricing and ownership.
BentoML Alternatives
BentoML Comparisons
Ready to try BentoML?
Visit the official website to get started.
Visit Official WebsiteAI Listing Jungle is an independent AI tools directory. Product names, logos, and trademarks belong to their respective owners.