Blog da Hanzo
Modelos de IA de fronteira, infraestrutura para agentes e a plataforma que impulsiona a próxima geração de aplicações inteligentes.
Idioma: Português (Brasil)
Comércio headless na era dos LLMs que compram sozinhos
Os compradores estão virando agentes. O que é preciso para um LLM conseguir ler, assinar e pagar sem uma pessoa no meio, e o que Hanzo entrega hoje para isso.
Sua IA está planejando te matar
Por que os modelos de fronteira falham quando vidas reais estão em jogo, e como Hanzo Kai 1.9 impõe uma segurança determinística.
Kai 1: decisões, não completações
Kai é o modelo de decisão da Hanzo, servido pela Hanzo API. Passe um estado explícito e uma pergunta com opções listadas, e ele devolve uma resposta tipada e calibrada: uma escolha, uma nota, um sim ou não, ou um adiamento justificado.
O que é um modelo de decisão?
Modelos generativos raciocinam em parágrafos sem limite. Modelos de decisão decidem em transições de estado tipadas e calibradas. Por isso a próxima fronteira da IA não é a geração, e sim a decisão.
Os principais pontos de dor das gestoras de investimento que a Hanzo AI resolve
Veja os desafios operacionais em private equity, venture capital e gestão de ativos, e como a nuvem soberana de IA da Hanzo, os modelos de raciocínio de fronteira e os fluxos agênticos aceleram a originação, a diligência e a execução.
O roteador é o registro
A Hanzo Cloud não tem arquivo OpenAPI versionado. A tabela de rotas viva é a fonte, projetada de três jeitos, e um teste de bijeção faz o build falhar se alguma projeção desviar. 1,362 operações em 963 paths, geradas por processo na hora da requisição.
Meio milhão de RPS em um GB10: o gargalo era a rede, não a máquina
Saímos para ver até onde o plano de dados da nossa nuvem conseguia ir em uma NVIDIA GB10. A resposta nos ensinou mais sobre as filas de recepção da NIC do que sobre o nosso próprio código, e mais do que dobrou a vazão no mesmo fio.
Chegou o Hanzo Datastore: um motor OLAP pronto para o pós-quântico
Um armazém colunar derivado do ClickHouse, reconstruído em torno da separação entre armazenamento e computação no Hanzo S3, otimizado por perfil e em tempo de link até cerca de metade da memória, sem gRPC e com um caminho para a coordenação pós-quântica sem líder.
Acabando com o Raft: do consenso ZooKeeper ao Lux Quasar, nativo
Como o Hanzo Datastore troca o motor NuRaft sob o ClickHouse Keeper pelo Lux Quasar — consenso pós-quântico e sem líder, ligado direto no servidor C++ — e mantém a API ZooKeeper que a replicação fala.
Proof of AI: uma nuvem de código aberto que paga os desenvolvedores sobre os quais roda
Hanzo Cloud se apoia em Proof of AI — inferência determinística que qualquer validador pode reverificar on-chain — e no compromisso de que 25% do que a nuvem ganha volta aos desenvolvedores de código aberto cujo código ela executa.
Hanzo Brain: grafo de conhecimento local-first para agentes
Um único arquivo SQLite que o seu agente lê em todo runtime. Zero idas e voltas ao LLM nas operações do grafo, FTS5 mais vetor mais extração de arestas tipadas na hora da escrita.
Zen: arquitetura MoE com 1T+ parâmetros
O LLM principal de Hanzo — um modelo Mixture of Experts de 1.04 trilhões de parâmetros, fundido a partir dos melhores modelos de linguagem, com treino distribuído e atestação do modelo on-chain.
A Hanzo publica provas formais para a infraestrutura de agentes de IA
Provas em Lean 4 verificadas por máquina para a segurança dos agentes, o protocolo MCP, o consenso PoAI e as operações da plataforma
BitDelta: servir 14 modelos Zen a partir de um único cluster de GPU
Como a compressão delta de 1 bit do BitDelta permite servir 14 variantes de modelos Zen a partir de infraestrutura de GPU compartilhada: a matemática, a arquitetura e os tradeoffs.
Da IA comercial aos modelos de fronteira: a década de infraestrutura da Hanzo
Doze anos construindo infraestrutura de IA — de um motor de recomendação em tempo real em 2014 a 94+ modelos de fronteira e uma blockchain pós-quântica em 2026. A história técnica de como chegamos até aqui.
A pilha completa do agente de IA: modelos, computação e ferramentas numa plataforma
A Hanzo AI apresenta a primeira plataforma que reúne mais de 100 modelos de IA, computação em nuvem, acesso a GPU e mais de 260 ferramentas MCP numa única conta de desenvolvedor.
GPUs H100 a $3.48/Hour — 72% mais baratas que a AWS
O Hanzo Bot abre acesso sob demanda a GPUs H100 para quem desenvolve agentes de IA a $3.48/hr — 72% abaixo do preço equivalente da AWS.
Rode agentes de IA por $5/Month: chega o Hanzo Bot
O Hanzo Bot chega com a hospedagem de agentes de IA mais barata do setor — a partir de $5/mo com crédito grátis, acesso integrado a mais de 100 modelos e GPUs H100 a $3.48/hr.
Transcrição de IA 85% mais barata que a OpenAI: preços multimodais para quem faz bots
O Hanzo Bot entrega fala para texto a $0.0009/minute — 85% mais barato que o OpenAI Whisper — e geração de imagens pelo menor preço do setor, $0.00013/step.
Análise profunda dos preços da Hanzo: cada modelo, cada plano, cada comparação
O detalhamento completo dos preços da Hanzo em modelos de IA, computação em nuvem, acesso a GPU e ferramentas, com comparações lado a lado contra cada grande concorrente.
Uma API para cada modelo de IA: chega a Hanzo AI Gateway
A Hanzo AI lança o primeiro gateway de IA multiprovedor sem margem do setor: uma chave de API para 100+ modelos de cada grande provedor, mais 14 modelos Zen próprios.
Zen4 Coder: 480B parâmetros, 92% menos ativos — o modelo de código MoE
A Hanzo AI lança o Zen4 Coder, um modelo de código Mixture of Experts de 480B parâmetros que ativa só 35B parâmetros por token e entrega inteligência de código de fronteira por uma fração do custo de computação.
Zero taxa de saída: a prática de preço da nuvem que precisa morrer
Taxa de saída é um imposto sobre o sucesso. A Hanzo Network inclui banda em cada nível, de 500 GB no plano de $5 a 120 TB no Ultra, sem cobrança de excedente.
Já disponíveis: Qwen3.5-35B-A3B e Mercury 2 — MoE eficiente e raciocínio de fronteira
Qwen3.5-35B-A3B (Apache 2.0, MoE multimodal) e o Mercury 2 da Inception já estão no gateway da Hanzo AI.
Já disponível: Gemini 3.1 Pro — o modelo de raciocínio de 1M tokens do Google
O Gemini 3.1 Pro do Google já está no gateway da Hanzo AI: janela de contexto de 1M tokens e raciocínio multimodal em texto, imagens, áudio, vídeo e código.
Já disponíveis: Claude Sonnet 4.6 e Qwen3.5-397B — MoE multimodal em escala
Claude Sonnet 4.6 e Qwen3.5-397B-A17B já estão no gateway da Hanzo AI: o lançamento mais recente da Anthropic ao lado do maior modelo MoE multimodal de código aberto.
Já disponíveis: Seed 2.0 da ByteDance e Qwen3-Coder-Next — raciocínio de fronteira e agentes de código
O Seed 2.0 Pro da ByteDance e o Qwen3-Coder-Next da Alibaba já estão no gateway da Hanzo AI: raciocínio multimodal de fronteira e agentes de código de código aberto.
Já disponíveis: GLM-5 (744B) e MiniMax M2.5 (230B) — dois gigantes de código aberto
GLM-5 e MiniMax M2.5, dois dos maiores modelos de código aberto já lançados, já estão no gateway da Hanzo AI.
Já disponíveis: Google Gemma 3n e Gemma 3 270M — a IA no dispositivo fica multimodal
A Gemma 3n do Google (multimodal no dispositivo) e a Gemma 3 270M (a menor Gemma até hoje) já estão no gateway da Hanzo AI.
Já disponíveis: Claude Opus 4.6 e GPT-5.3 Codex no gateway da Hanzo
O Claude Opus 4.6 da Anthropic e o GPT-5.3 Codex da OpenAI já estão no gateway da Hanzo AI: mesma API, mesma chave, zero de acréscimo.
Hanzo Cap Table: gestão de participação para startups
Chegou o Hanzo Cap Table: gestão de equity, cenários e preparo para o 409A, sem o preço da Carta.
Em inglês
Ainda sem tradução: estes artigos abrem em inglês.
Introducing Enso — one API, routed to the best frontier intelligence
Enso is Hanzo's learned router: no single frontier model leads every benchmark, so Enso routes each request to the model most likely to win it — and learns from your feedback as it goes. Microsecond routing on a CPU, a transparent per-request meter, and a 1% fee that pays for itself. Here is how it works, the measured results, and the cost-transparency angle a monolith cannot offer.
Route every prompt to the right model — and cut AI cloud costs by up to 90%
Hanzo Router places each request on the cheapest model that can still serve it — reuse a local model for free, load one that fits, or fall through to cloud. Here's the idea, what it feels like in production (qualitative), and the honest cost arithmetic (quantitative) — no fabricated benchmark.
Enterprise Cloud Without Enterprise Pricing: 96 vCPUs at $3,999/Month
Hanzo Network launches Business through Ultra enterprise cloud tiers — dedicated CPU machines from 8 to 96 vCPUs with 71–81% cost advantage over hyperscaler equivalents.
Hanzo Network: 10–54% Cheaper Than DigitalOcean, Lightsail, and Vultr
Hanzo Network launches a developer cloud that undercuts DigitalOcean, AWS Lightsail, Vultr, and Linode by 10–54% — with zero egress fees, DDoS protection, and consistent global pricing included.
Zen4: Abliterated AI Models for Every Scale
Announcing the full Zen4 family: mini (4B) through ultra (1T MoE), all abliterated. Eight models covering every scale from edge to cloud, with no refusal behavior and full capability access.
Introducing Zen4: Open Foundation Models from 4B to 1T+
Zen4 is a complete lineup of open AI models spanning from 4B to over 1 trillion parameters, featuring consumer, coder, and ultra tiers.
Hanzo Browser Extension: AI in Every Tab
Bringing AI capabilities to your browser - summarize pages, answer questions, and automate workflows.
Hanzo Dataroom: Secure Document Sharing with Analytics
Introducing Hanzo Dataroom — secure document sharing with per-page analytics, watermarking, and granular access controls for fundraising and M&A.
Hanzo ML Platform: End-to-End Machine Learning Infrastructure
Announcing the unified Hanzo ML Platform — training, serving, pipelines, feature store, model registry, and evaluation in one integrated system.
Zen Reranker: Neural Reranking at 30x Compression
Zen Reranker delivers 7680-dimensional neural reranking with a 31.87x BitDelta compression ratio, designed for RAG pipelines and integrated with Hanzo and Zoo decentralized search networks.
Hanzo Dev: AI Coding Agent for Your Terminal
Hanzo Dev launches — an AI coding agent that lives in your terminal, understands your codebase, and writes production-quality code.
Zen VL: Vision-Language Models with Function Calling
Zen VL is a family of vision-language models at 4B, 8B, and 30B -- each with instruct and agent variants -- supporting OCR in 32 languages, GUI navigation, spatial grounding, and native function calling with visual context.
Zen Artist: Image Generation Reimagined
Introducing Zen Artist - our multimodal image generation model with unprecedented control and quality.
Zen Omni: Unified Multimodal AI
Zen Omni is a 30B MoE unified multimodal model with Thinker-Talker architecture, handling text, vision, and audio in a single model with real-time speech-to-speech at under 300ms latency.
MCP: 260 Tools for AI Models
How we built 260+ tools using Model Context Protocol, enabling AI models to interact with the world.
Zen Designer: 235B Vision-Language Model
Zen Designer is a 235B MoE vision-language model with 22B active parameters, supporting image analysis, video understanding, OCR in 32 languages, and native design reasoning.
Zen Max: 671B Reasoning Model
Zen Max is a 671B MoE reasoning model with 384 experts, 256K context, and abliterated base weights -- achieving AIME 2025 99.1%, SWE-Bench 71.3%, and BrowseComp 60.2%.
One Billion Dollars in Client Revenue
Hanzo AI has driven over $1 billion in cumulative revenue for our clients through AI-powered marketing and commerce infrastructure.
Zen Coder: Code AI from 4B to 480B
Zen Coder is a family of code-specialized models spanning 4B edge to 480B frontier, with 128K context, extended thinking up to 512K tokens, MCP integration, and support for 100+ programming languages.
Hanzo Operative: Computer Use for AI Agents
Introducing Hanzo Operative — enabling AI agents to use computers like humans: screen capture, mouse, keyboard, and application interaction.
Hanzo Flow: Visual AI Workflow Builder
Hanzo Flow launches — a visual drag-and-drop builder for complex AI workflows. Connect models, tools, and APIs without writing integration code.
Zen Guard: Multilingual AI Safety Classification
Zen Guard is an 8B multilingual safety classifier covering 119 languages and 9 harm categories, with a three-tier severity system and 5ms/token streaming latency.
Introducing Hanzo Console: Unified LLM Observability
Hanzo Console launches — a unified development environment for observing, debugging, and optimizing LLM applications across all providers.
Zen Embedding: #1 Multilingual Retrieval
Zen Embedding reaches #1 on the MTEB multilingual leaderboard with a 70.58 score, supporting 100+ languages and Matryoshka representation learning across four dimension sizes.
Hanzo Experiments: Feature Flags and A/B Testing
Introducing Hanzo Experiments — feature flags, A/B testing, and progressive rollouts with statistical rigor.
Zen Nano: 0.6B Edge AI Model
Zen Nano is a 0.6B on-device AI model built for mobile and embedded deployment, achieving 44K tokens/sec on M3 Max with a 40K context window.
Zen Musician: AI-Generated Music That Sounds Human
Introducing Zen Musician - our AI music generation model that creates original compositions in any style.
Jin 2.0: The Next Generation of Multimodal AI
Announcing Jin 2.0, a major upgrade to our unified multimodal AI architecture with expanded capabilities and improved performance.
Case Study: Keek — AI-Powered Social Media Transformation
How Hanzo integrated AI infrastructure into the Keek social platform — content recommendation, multimodal moderation, and creator tools processing 12M daily content items.
ACI: The AI Compute Infrastructure Network
Introducing ACI, a decentralized network for AI compute that enables trustless, verifiable AI inference.
Zen Video: Generative Video at Scale
Introducing Zen Video - our generative video model for creating high-quality video content from text and images.
Hanzo Partners with Personas Social to Power Keek's AI
Hanzo AI partners with Personas Social Inc. to integrate AI-powered features into the Keek social platform.
Hanzo Notebooks: Managed Jupyter with GPU Access
Introducing Hanzo Notebooks — managed Jupyter workspaces with on-demand GPU access and pre-installed ML frameworks.
Candle: Rust-Native Machine Learning
Introducing our investment in Candle, the Rust ML framework powering Hanzo's next-generation inference.
Hanzo Sign: Electronic Signatures Without the Enterprise Tax
Introducing Hanzo Sign — legally binding electronic signatures with audit trails, templates, and API access at a fraction of DocuSign's price.
Hanzo CX: Complete Customer Experience Platform
Introducing Hanzo CX — a unified customer experience platform with omnichannel inbox, AI-assisted responses, and full conversation history.
Zen Coder: Code Generation That Actually Works
Building Zen Coder - our code generation model trained on real software engineering workflows.
Zen Dub: Voice Cloning and AI Dubbing
How we built Zen Dub - an AI system for voice cloning and automatic dubbing in 100+ languages.
LLM Infrastructure: Running AI at Scale
How we built infrastructure to serve billions of LLM requests for commerce applications.
Hanzo Auto: AI Workflow Automation
Introducing Hanzo Auto — AI-powered workflow automation with 280+ integrations and a visual builder.
Hanzo CRM: Modern Customer Relationship Management
Introducing Hanzo CRM — a modern, AI-enhanced CRM for teams that want to close deals, not manage software.
Zen Agent: Building AI That Actually Does Things
Introducing Zen Agent - our framework for building AI systems that can take action in the real world.
Zen Integration: AI That Follows Your Rules
Introducing Zen, our system for ensuring AI follows business rules, compliance requirements, and brand guidelines.
Hanzo Insights: Product Analytics That Respects Privacy
Introducing Hanzo Insights — product analytics with event tracking, funnels, cohorts, and session replay, without selling user data.
Hanzo Edge: High-Performance API Gateway
Introducing Hanzo Edge — a high-performance API gateway with sub-millisecond routing, rate limiting, and authentication at the edge.
Gym: Distributed Training for the Rest of Us
Introducing Gym - our platform for distributed AI model training that turns the world's GPUs into a supercomputer.
Jin: Unified Multimodal AI Architecture
Introducing Jin, our unified architecture for multimodal AI that powers the next generation of Hanzo intelligence.
LLM Inference at the Edge: Our llama.cpp Journey
How we brought large language models to edge devices using llama.cpp and what we learned along the way.
Hanzo Observability: Metrics, Logs, and Traces in One Platform
Launching the Hanzo Observability stack — unified metrics, logs, and distributed tracing with OpenTelemetry-native ingestion.
hanzo.vim: AI-Powered Vim for Terminal Purists
Bringing AI capabilities to Vim without sacrificing the terminal-native experience.
Identity NFTs: Portable Commerce Identity
Introducing Identity NFTs: blockchain-based portable identity for commerce.
Open Source at Hanzo: Building in Public
Announcing Hanzo's open-source strategy — why we're open-sourcing our core infrastructure and introducing revenue sharing for contributors.
HKE: Hanzo Kubernetes Engine
Launching HKE — managed Kubernetes that eliminates the operational burden without limiting what you can do.
Building Our ML Framework
Why we built a custom ML framework and what we learned along the way.
Case Study: Bellabeat — Scaling a Women's Health Platform
How Hanzo helped Bellabeat scale their women's health wearable platform to $35M in projected revenue through CMO/CTO services, marketing automation, and data analytics.
Hanzo Search: Full-Text Search That Just Works
Introducing Hanzo Search — full-text search with typo tolerance, faceting, and sub-millisecond query times.
Agent SDK: Build Intelligent Assistants
Introducing the Hanzo Agent SDK: tools for building intelligent commerce assistants.
Hanzo Platform: Git Push to Production
Launching Hanzo Platform — a PaaS that deploys your code from git push to production with zero DevOps configuration.
Multi-Modal AI for Commerce
How we are combining vision, language, and structured data for next-generation commerce AI.
Hanzo Tasks and Queues: Durable Background Execution
Launching Hanzo Tasks and Queues — durable workflow execution and message queues for reliable background processing.
Case Study: Damon Motorcycles — 500x ROI Campaign
How Hanzo delivered a 500x ROI marketing campaign for Damon Motorcycles, generating a 230% increase in qualified leads for their electric motorcycles.
The Context Layer: Our Early Work on Multi-Model State Management
How we built a context management protocol for multi-model AI pipelines — early research that shaped how we think about AI state.
Hanzo KMS: Secrets Management Done Right
Introducing Hanzo KMS — end-to-end encrypted secrets management with environment sync, rotation, and audit trails.
Hanzo Storage: S3-Compatible Object Storage
Launching Hanzo Storage — S3-compatible object storage with integrated CDN and no egress fees.
Case Study: Casper — Enterprise Blockchain from Concept to Mainnet
How Hanzo helped Casper Labs architect and launch an enterprise-grade blockchain — from the Rust pivot to mainnet launch and DEVxDAO founding.
Hanzo SQL: Managed PostgreSQL with Zero Ops
Launching Hanzo SQL — managed PostgreSQL with automatic scaling, high availability, and zero operational overhead.
Introducing the Hanzo Agent Framework
Announcing the Hanzo Agent Framework: building blocks for intelligent automation in commerce.
Hanzo Base: Backend-as-a-Service for Modern Applications
Introducing Hanzo Base — a complete backend-as-a-service with database, auth, storage, and realtime capabilities.
Hanzo Cloud: Managed Infrastructure for Commerce
Introducing Hanzo Cloud: fully managed commerce infrastructure with enterprise-grade reliability.
Hanzo DNS and Networking: Programmable Infrastructure
Launching Hanzo DNS and Networking — programmable DNS with service discovery and zero-trust virtual networks.
Webhooks: Real-Time Event Delivery
Announcing Hanzo Webhooks: reliable, secure, real-time event delivery for your integrations.
Case Study: Unikoin Gold — 120,000 ETH Token Launch
How Hanzo helped Unikrn raise 120,000 ETH in their token launch, combining blockchain infrastructure with regulatory compliance across 15+ jurisdictions.
The Hanzo SDK Ecosystem
Announcing official SDKs for JavaScript, Python, Ruby, Go, and PHP, plus the new SDK development kit.
Hanzo Functions: Serverless Compute with Zero Cold Starts
Introducing Hanzo Functions — serverless compute with zero cold starts, built for event-driven commerce workloads.
The Hanzo API Gateway
Introducing the Hanzo API Gateway: unified access, better security, and improved developer experience.
Co-Founding the First SEC-Approved Crowdfunding Token
Hanzo co-founded the first SEC-approved crowdfunding token offering, bridging traditional crowdfunding with tokenized securities.
ML-Powered Analytics: From Dashboards to Decisions
How we are using machine learning to transform analytics from passive reporting to active decision support.
Hanzo Payments: Unified Payment Processing for Global Commerce
Launching Hanzo Payments — unified payment processing with intelligent routing, fraud detection, and multi-currency support.
Checkout 2.0: Conversion Through Simplicity
Announcing Checkout 2.0, our redesigned checkout experience built for maximum conversion.
Hanzo Identity: Authentication That Scales with Your Business
Introducing Hanzo Identity — enterprise-grade authentication and access management built for commerce platforms.
Commerce AI: What We Learned in 2017
Lessons from a year of building and deploying AI systems for commerce.
42 Million in Client Sales: What Techstars Taught Us
Reflecting on Techstars Demo Day and $42M in client sales generated through the Hanzo platform.
Hanzo Joins Techstars '17
Hanzo has been selected for Techstars 2017, accelerating our mission to power intelligent commerce.
Introducing the Hanzo Platform
Crowdstart evolves into Hanzo: a complete commerce platform for the modern era.
AI-Powered Product Recommendations
How we built collaborative filtering and content-based recommendations into the Crowdstart platform.
Hanzo Analytics: Real-Time Intelligence for Commerce
Launching Hanzo Analytics — real-time behavioral intelligence for commerce teams who need answers now, not tomorrow.
Earle: Genetic Algorithms for Marketing Optimization
Introducing Earle, our genetic algorithm system for evolving high-performing marketing campaigns.
Real-Time Analytics: From Data to Decisions
How we built real-time analytics into Crowdstart and what we learned about data-driven commerce.
Astle.js: Reactive Commerce Components
Releasing Astle.js, our open-source library for building reactive commerce interfaces.
Cloud-Native Commerce: Why Architecture Matters
How we built Crowdstart as a cloud-native platform from day one, and why this matters for commerce.
Introducing Crowdstart: Commerce for the Crowdfunding Era
Announcing Crowdstart, a new platform enabling creators to build sustainable businesses from successful crowdfunding campaigns.
PubSub: The Event-Driven Foundation
How we built a publish-subscribe system that became the nervous system of our entire platform.
KV: Distributed State for the Real World
Building a key-value store that could handle the chaos of distributed systems - our second foundational project.
The Datastore: Where It All Began
The first building block of what would become Hanzo - a flexible datastore designed for the next generation of applications.