# Models URL: https://docs.hanzo.ai/docs/models > Enso routes, Kai decides, Zen reasons, Policy governs — the model families, what each is for, and the live catalogue with every id you can pass. **After this page you know which family answers which kind of question, which ones you can download, and which ids the gateway serves right now.** ## Five roles | Family | Role | Weights | Reach it at | Status | | ------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------ | --------------------------------------------------------------------------- | | **[Enso](https://docs.hanzo.ai/docs/models/enso)** | routes: three paid tiers, each a chain of frontier models under one id and one price, and the `auto` router | router code open ([hanzoai/engine](https://github.com/hanzoai/engine)); tiers hosted | `enso-auto`, `enso-flash`, `enso-pro`, `enso-ultra`; `model: "auto"` | shipped | | **[Kai](https://docs.hanzo.ai/docs/models/kai)** | decides: typed, calibrated answers to bounded questions | hosted, not published; served by API only | `model: "kai"` on [`POST /v1/decisions`](https://docs.hanzo.ai/docs/decisions) | live: kai-1.2, $0.021 per million input tokens | | **[Zen](https://docs.hanzo.ai/docs/models/zen)** | reasons: agentic coding that runs locally, marketing copy and assets; also vision, speech, embeddings | open, on [Hugging Face](https://huggingface.co/zenlm) | `zen*` ids on `/v1/chat/completions` | shipped | | **[Creative AI](https://docs.hanzo.ai/docs/models/creative)** | generates: cinematic video, high-fidelity imagery, 3D meshes, foley, voice, music | proprietary checkpoints over open foundations; private weights | studio nodes (`studio.hanzo.ai`) & gated API | research preview · [Apply](https://hanzo.ai/research-access?track=creative) | | **Policy** | governs: deterministic allow / ask / deny | — | your rules, in every Decision Program | a part of Hanzo Decision, not a model | The split is by the shape of the answer. An open question — write, explain, plan — needs generation, so it goes to Zen. A bounded one — which model, which tool, is this done, allow or deny — has a known answer space, so it goes to Kai, which answers it without generating text. Creative media synthesis — video, images, 3D, audio — runs on proprietary Creative AI checkpoints in Studio. Enso sits in front and sends each operation to the one that should answer it. Policy has the last word on any action, and a model can make a verdict stricter, never looser. ## Other lines | Name | What it is | Status | | ------------------ | ------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ | | **Kai-1.7** | multimodal decision intelligence and adaptive reasoning | early access preview · [Guide](https://docs.hanzo.ai/docs/decisions/early-access) · [Request access](https://hanzo.ai/research-access?track=kai) | | **Zen 7** | the next Zen generation; succeeds Satori | research preview — no weights, no id to call · [Request access](https://hanzo.ai/research-access?track=zen) | | **Koma** | cinematic video generation and shot continuity | research preview · [koma](https://hanzo.ai/koma) · [Apply](https://hanzo.ai/research-access?model=koma) | | **Iro** | high-fidelity creative image synthesis and art direction | research preview · [iro](https://hanzo.ai/iro) · [Apply](https://hanzo.ai/research-access?model=iro) | | **Mori** | production-ready geometric 3D mesh and PBR generation | research preview · [mori](https://hanzo.ai/mori) · [Apply](https://hanzo.ai/research-access?model=mori) | | **Oto** | synchronized foley sound effects and acoustic modeling | research preview · [oto](https://hanzo.ai/oto) · [Apply](https://hanzo.ai/research-access?model=oto) | | **Koe** | expressive speech performance and dialogue synthesis | research preview · [koe](https://hanzo.ai/koe) · [Apply](https://hanzo.ai/research-access?model=koe) | | **Uta** | structural music composition and multi-track stems | research preview · [uta](https://hanzo.ai/uta) · [Apply](https://hanzo.ai/research-access?model=uta) | | **Satori** | a video-generation line, never trained | retiring; replaced by Zen 7 | | **Jin** | a multimodal model specified in [HIP-0003](https://hips.hanzo.ai/docs/hip-0003-jin-multimodal-ai-architecture) | not built; no weights | | **Enso Diffusion** | a sparse mixture-of-experts diffusion transformer, forked from DiT-MoE: [zenlm/enso](https://github.com/zenlm/enso) | research code, no released weights | | **Enso Browser** | a Firefox-based desktop browser | not released | ## The live catalogue Every model below answers on one address with one key. Pass the `id` as `model` and the rest of the request is the same whichever you pick. The one exception is `kai`, listed with `"outputs": ["decision"]`: it answers typed questions on [`POST /v1/decisions`](https://docs.hanzo.ai/docs/decisions), not chat. ```bash curl https://api.hanzo.ai/v1/chat/completions \ -H "Authorization: Bearer $HANZO_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"","messages":[{"role":"user","content":"Hello"}]}' ``` The table is fetched from [`/v1/models`](https://docs.hanzo.ai/docs/openapi/ai) in your browser when this page loads, so it is the catalogue the gateway is serving right now rather than a copy written down when the page was built. The same list, by family, needs no key: ```bash curl -s https://api.hanzo.ai/v1/models \ | jq -r '.data[] | select(.id | test("^(zen|enso)")) | "\(.id)\t\(.owned_by)\t\(.pricing.input_per_million)/\(.pricing.output_per_million)"' ``` The live model catalogue: [GET https://api.hanzo.ai/v1/models](https://api.hanzo.ai/v1/models) ## What a rate means Rates are per million tokens (`pricing.input_per_million`, `output_per_million`; `pricing.prompt` and `completion` state the same rates per token, as OpenRouter does), input and output priced separately, and they are the same whether you call from the CLI, an SDK, HTTP or an MCP tool — the price is a property of the model, not of the surface you reach it through. [Pricing](https://docs.hanzo.ai/docs/pricing) explains how usage becomes a bill. [Credits](https://docs.hanzo.ai/docs/credits) covers what happens when the balance runs out. ## Hugging Face Hub & Model Registry Hanzo AI maintains a public model and system card registry across [Hugging Face (`huggingface.co/hanzoai`)](https://huggingface.co/hanzoai) and [ZenLM (`huggingface.co/zenlm`)](https://huggingface.co/zenlm), organizing its first-party architecture across 5 functional families: 1. **Kai — Unified Multimodal Decision Intelligence (`hanzoai/kai-*`)**: Calibrated, typed decision models. Hosted API on `POST /v1/decisions` (`kai-1.3`, `kai-1.4`, `kai-1.5`, `kai-1.6`, and the unified multimodal target `kai-1.7`), alongside specialized baselines (`kai-1-agent`, `kai-1-multilingual`). 2. **Enso — Intelligent Routing (`hanzoai/enso-*`)**: Dynamic prompt routing across cost, latency, and quality tiers (`enso-auto`, `enso-flash`, `enso-pro`, `enso-ultra`, `enso-free`). 3. **Zen — Generative Intelligence (`zenlm/zen6*`)**: Open-weight foundation models for agentic coding, reasoning, and multimodality (`zen6`, `zen6-flash`, `zen6-coder`, `zen-vl`, `zen-embedding`, `zen-reranker`). 4. **Guard — Safety & Oversight (`hanzoai/guard`, `zooai/lifeguard`)**: Deterministic policy gateways and consequence-grounded evaluation suites (redirected from `zoo-labs/lifeguard`). 5. **Agent Systems (`hanzoai/kata`, `hanzoai/gen`)**: Autonomous DAG execution and software engineering agent runtimes. ### Interactive Spaces Try models and inspect benchmarks in real-time on Hugging Face Spaces: - [**Leaderboard**](https://huggingface.co/spaces/hanzoai/leaderboard): Open Decision Model Arena comparing Kai, Jev 1.13, and frontier LLMs. - [**Kai Playground**](https://huggingface.co/spaces/hanzoai/kai-playground): Interactive typed question console (`boolean`, `choice`, `score`). - [**Enso Router Simulator**](https://huggingface.co/spaces/hanzoai/enso-router): Real-time prompt complexity and cost router preview. - [**Guard Arena**](https://huggingface.co/spaces/hanzoai/guard-arena): Adversarial prompt injection and policy boundary testing. ## Specifications | HIP | Subject | Status | | ------------------------------------------------------------------------------ | --------------------------------------------------------------- | ------ | | [HIP-0511](https://hips.hanzo.ai/docs/hip-0511-model-families) | Model families: every line, its HIP, its API and where it runs | Living | | [HIP-0039](https://hips.hanzo.ai/docs/hip-0039-zen-model-architecture) | Zen model architecture | Final | | [HIP-0904](https://hips.hanzo.ai/docs/hip-0904-zen6) | The `zenlm/zen6*` repositories on Hugging Face: what each holds | Final | | [HIP-0510](https://hips.hanzo.ai/docs/hip-0510-enso-learned-router) | Enso: learned per-request routing | Final | | [HIP-1332](https://hips.hanzo.ai/docs/hip-1332-kai-the-decision-model) | Kai: the decision model and the decision plane | Draft | | [HIP-0003](https://hips.hanzo.ai/docs/hip-0003-jin-multimodal-ai-architecture) | Jin: a multimodal model that was not built | Draft |