Files

1 line
8.1 KiB
JSON
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{"text":["Hanzo Enterprise","Give every team AI.","Run it where you choose.","Models, agents and one shared workspace for everyone in your company, in your cloud, on your servers or fully offline.","Get Enterprise plan","Build on Hanzo Platform","Unlimited members","24/7 engineering support","Runs fully offline","Where it runs","01 / 04","Hanzo Cloud","We run it for you. Start today. On Hanzo Base, your organization's data is its own database.","Your cloud","Inside your VPC. Hanzo runs in your own cloud account, on your network.","Your servers","On premises. On hardware in your data center, beside the systems you already run.","Air-gapped","Fully offline. Sealed inside your network, with models served on machines you control.","What you get","What Enterprise includes.","Your own infrastructure, dedicated compute, and engineering support around the clock.","Your infrastructure","Run Hanzo in your cloud, on your own servers, or fully offline.","Dedicated compute","Compute set aside for your organization alone.","Your own models","Train and host your own models, on your own data.","Commitments in writing","An uptime guarantee and a security review, both in your contract.","Engineering support around the clock, and hands-on onboarding to get your teams started.","Your whole company","Unlimited members, single sign-on, roles and an audit log.","Deployment","Run it where your data lives.","One platform, four places to run it. Choose one, or start in our cloud and move when you are ready.","Fastest start","Most control","We run it for you","Start today. On Hanzo Base, your organization's data is its own database.","Inside your VPC","Hanzo runs in your own cloud account, on your network.","On premises","On hardware in your data center, beside the systems you already run.","Fully offline","Sealed inside your network, with models served on machines you control.","Your own GPUs","Run the models on machines you own.","Zen 6 runs on one DGX Spark. Zen 6 Max wants a rack of Blackwell servers. What we measured, and what a rack is made of.","Zen 6 on one DGX Spark, as Hanzo measured it","Prompt","Prefill time","Prefill rate","512 tokens","1.9 s","270 tokens a second","2,048 tokens","0.8 s","2,658 tokens a second","8,192 tokens","4.5 s","1,835 tokens a second","16,384 tokens","9.6 s","1,701 tokens a second","32,768 tokens","23.2 s","1,414 tokens a second","A cold prompt of about that many tokens on a quiet box, measured Sep 20, 2026: NVIDIA DGX Spark (GB10), 121 GiB unified memory, shared with the benchmark's other jobs; zen6, NVFP4 with FP8 attention, weights 21.6 GiB (serve-spark-zen6.sh).","NVIDIA DGX Spark: GB10, 273 GB/s memory bandwidth","Zen 6 on three machines","Zen 6 Max","We recommend at least four 8-GPU NVIDIA Blackwell servers, B300 or B200, for Zen 6 Max on your own premises. Routing cuts the average inference work a request needs. It does not cut the memory needed to keep every specialist ready.","DGX B300","GPUs","8 x B300","GPU memory","8 x 288 GB, 2,304 GB","Cluster network","8 x 800 Gb/s InfiniBand or Ethernet","Data cache","8 x 3.84 TB","NVIDIA DGX B300 user guide: 8 x 288 GB GPU memory","DGX B200","8 x B200","1,440 GB","8 x ConnectX-7, up to 400 Gb/s","NVIDIA DGX B200 user guide: 1,440 GB total GPU memory","Four B300 servers hold 9,216 GB of GPU memory; four B200 servers hold 5,760 GB.","Planning range","Four 8-GPU servers is where a qualification starts.","Qualification","One pool for each specialist, so a busy class of work never takes memory from another.","Isolated production pools","Two independent replicas of those pools across failure domains.","Redundant pools","Around the servers","NVLink and NVSwitch inside each server.","400 or 800 Gb/s RDMA wherever a specialist spans servers.","About 31 TB of NVMe in each server (8 x 3.84 TB).","Separate sandbox workers for coding agents.","A high-availability control cluster.","Final capacity and performance commitments come from qualifying your workload: context length, concurrency, routing mix, latency, and failover.","Proof","Results on the record.","Our models' scores come from research runs anyone can open. Customer results come from the case studies of launches Hanzo ran.","16 of 16","Decision Suite tasks won · Kai vs Jev","Every task of the suite, its row linking its runs and how to re-run it.","See the runs","$8.4M","in bikes sold in 30 days","Damon Motorcycles","CES launch and preorders","$7M+","raised in preorders","KANOA","Crowdfunding and preorders","169M","people watched TrillerFest","Triller","Growth marketing","$2.5M","raised on Indiegogo","SKULLY","Crowdfunding","$650M","CSPR peak market value","Casper Labs","Network launch","250,000","email signups","Bellabeat","Preorders","All customer stories","Partners","Work with Hanzo.","Refer customers, resell Hanzo under your own brand, or have Hanzo’s agency build it with you.","Refer customers","Apply to refer organizations to Hanzo. The terms are agreed with each affiliate we approve.","The affiliate programme","White-label: resell under your brand","Your own AI agency, under your brand, on your domain.","$999 a month","Ask about White-label","Have Hanzo build it","Agency, Forward Deployed, Embedded Pod: Hanzo’s agency ships the work with you, from one workstream to an embedded team.","From $4,999 a month","Hanzo Agency","Hanzo runs in your cloud and on these. They are the clouds and the silicon Hanzo deploys on, not partners or customers.","Security","Ready for your security review.","A security review is part of every Enterprise contract. We answer your questionnaire against the code, and the engineers who wrote it walk your reviewers through it.","Single sign-on","Sign in through your own OpenID Connect provider. SCIM 2.0 creates, updates and removes accounts from your directory.","Your data, apart","On Hanzo Base, each organization's data is its own database file, kept apart from every other organization. Identity comes only from a verified token.","Audit log","Every request is recorded: who acted, from where, what they called and the status it returned.","Roles and second factors","Grant access by organization, workspace and project. Every account can add an authenticator app, or a code by SMS or email.","How Hanzo is secured","Trust center","Questions","How is Enterprise priced?","Each contract is priced for your organization: where Hanzo runs and the compute you need. Members are unlimited.","for a quote.","Talk to sales","Where do the savings figures come from?","Every rate is read from our price list and our plan list when the page opens; the volumes, the people and the GPUs are yours. The figure for your own GPUs counts them on all month at an hourly rate and leaves out the Enterprise agreement, which our team prices with you.","Can Hanzo run fully offline?","Yes. Hanzo runs air-gapped on your own servers, with models served on machines you control.","How is our data used?","Your data is used to run your service. Training Hanzo models on it takes your administrator's choice or a written agreement.","Read the Privacy Policy","Which identity providers work?","Your own OpenID Connect provider, for single sign-on. SCIM 2.0 creates, updates and removes accounts as your directory changes.","Can we start on Team and move up?","Yes. Team covers 2 to 100 people today, with single sign-on, roles and an audit log. Move to Enterprise when you want your own infrastructure, dedicated compute or more people.","Compare plans","Tell us what you want to build.","Share a few details about your company. We come back with a plan: where Hanzo runs, what it costs and how you start.","Or email","[email protected]","02 / 04","03 / 04","04 / 04"],"links":["/enterprise/start","https://platform.hanzo.ai","https://www.nvidia.com/en-us/products/workstations/dgx-spark/","/benchmarks/zen-6","/zen/zen6-max","https://docs.nvidia.com/dgx/dgxb300-user-guide/introduction-to-dgxb300.html","https://docs.nvidia.com/dgx/dgxb200-user-guide/introduction-to-dgxb200.html","/benchmarks#decision-suite","/customers/damon-motorcycles","/customers/kanoa","/customers#trillerfest","/customers#skully","/customers#casper-blockchain","/customers#bellabeat","/customers","/affiliate","/contact-sales","https://hanzo.agency","/security","/trust","/privacy","/pricing","mailto:[email protected]"]}