# Models — Hanzo AI > Explore frontier models and open-weight architectures. Access Enso, Zen, and 500+ partner models through one unified OpenAI-compatible API. Models # Frontier AI families Proprietary and open weight models for text, decisions, video, image, and more — one account, one API key. [Get API key](https://platform.hanzo.ai/api-keys)[Every model](#catalog) Live from api.hanzo.ai POST /v1/chat/completionsexample Enso Zen 6 Claude Fable 5 { "model": "enso", "messages": [{ "role": "user", "content": "Who are you?" }] } EnsoHanzo's proprietary frontier model — Opus-class reasoning by default with 1M-context overflow. 900Ktext Three families ## Enso routes. Kai decides. Zen reasons. - routesEnsoPicks the model for every call, in every modality.Explore Enso → - decidesKaiAnswers a choice, a score or a yes/no, with the probability of each.11 · Suites won · Kai vs JevExplore Kai → - reasonsZenOpen weights for the code, the copy, the images and the voice.Zen 6 and Zen 6 Flash now · Zen 7 in research previewExplore Zen → Enso vs Zen ## Proprietary orchestration, on open foundations ### Enso Proprietary · Hanzo Cloud only - Flash, Pro and Ultra presets - OpenAI- and Anthropic-compatible - Metered and audited per organization [Explore Enso →](https://hanzo.ai/enso) ### Zen Open weights · Zoo Labs Foundation - Free to download and self-host - Or call it on Hanzo Cloud - From a 501(c)(3) non-profit [Explore Zen →](https://hanzo.ai/zen) ## Enso models [Ensoenso900KHanzo's proprietary frontier model — Opus-class reasoning by default with 1M-context overflow.text](https://hanzo.ai/models/hanzo/enso) [Enso Flashenso-flash900KFast, economical Enso tier for high-volume, low-latency everyday work, with 1M-context overflow.text](https://hanzo.ai/models/hanzo/enso-flash) [Enso Ultraenso-ultra1MAdaptive fan-out — probes a task-appropriate model, escalates to a top-K panel only when needed, then verifies-then-selects the best answer.text](https://hanzo.ai/models/hanzo/enso-ultra) [Enso: the router, its presets and its runs →](https://hanzo.ai/enso) ## Zen models Open weights, made with [Zoo Labs Foundation](https://zoo.ngo). Download every Zen model at [huggingface.co/zenlm](https://huggingface.co/zenlm), or call it here. [Zen6zen61Mtext](https://hanzo.ai/models/hanzo/zen6) [Zen6 Flashzen6-flash1Mtext](https://hanzo.ai/models/hanzo/zen6-flash) [Zen5 (Default)zen51MCanonical Zen5 default. a 35B frontier MoE (3B active) (35B total / 3B active per token, released Apr 2026, Apache-2.0). 256K context, agentic-trained, OpenAI + Anthropic API. The everyday Zen5 chat model.text](https://hanzo.ai/models/hanzo/zen5) [Zen5 Prozen5-pro1MZen Flash IQ2_XXS-imatrix weights (81 GB GGUF on zenlm/zen-5-pro-gguf). 284B total / 37B active per token, 1M context, asymmetric routed-MoE quant. Fits a single 128 GB Apple Silicon / DGX Spark / H100 80 GB.text](https://hanzo.ai/models/hanzo/zen5-pro) [Zen5 Coderzen5-coder1MCode-specialized Zen5 tier. 80B sparse MoE tuned for repo-scale code understanding, agentic refactoring, and tool-use coding loops.text](https://hanzo.ai/models/hanzo/zen5-coder) [Zen5 Flashzen5-flash1MSmallest and cheapest text-only Zen5 chat tier. 4B-class dense, sub-100ms TTFT, 32K context. For high-volume routing and simple agent loops.text](https://hanzo.ai/models/hanzo/zen5-flash) [Zen VL — Vision-Languagezen-vl1MReads images and reasons over them — visual Q&A, document and chart understanding, grounded captioning.text](https://hanzo.ai/models/hanzo/zen-vl) [Zen Embeddingzen-embedding33KDense text embeddings for semantic search, retrieval, and clustering.embeddings](https://hanzo.ai/models/hanzo/zen-embedding) Zen 7zen7 The next open-weight generation after Zen 6, in research preview. Research preview[Request access](https://hanzo.ai/research-access?track=zen) [Run Zen: the docs →](https://docs.hanzo.ai/docs/models/zen) ## Kai decision models [Kaikai33KHanzo Kai is a structured decision model answering typed questions at /v1/decisions with calibrated probabilities and zero output tokens. Full multimodal decision architecture (~850M parameters, 32K reach); native vision and audio towers: Kai-1.7 target.TextStateVision (Kai-1.7 target)](https://hanzo.ai/models/hanzo/kai) [Decision Benchmarks11 suites won vs jevAhead of Jev on 11 suites: AG News, DAIR Emotion, Banking77, Support triage, Email spam, Phishing, Toxicity, RAG relevance, Model routing, Typed decisions, MASSIVE, 51 languages. 84.4% mean accuracy across these 11 suites, against Jev's 76.6%. 100.0% of repeated requests answer identically, against Jev's 44.2%.benchmarks](https://hanzo.ai/kai#benchmarks) [Autonomous Agent Steeringdecision-readyA choice, a score or a yes/no, each with its probabilities, for agent loops such as Hanzo Dev's.choicescorenoul](https://hanzo.ai/kai#types) [Kai: decisions and their benchmarks →](https://hanzo.ai/kai) ## Creative models Video, images, 3D, sound effects, voice and music, each its own model, in research preview. [Komakoma-1Research previewCinematic video generation, character continuity, motion, animation, and shot-level creative control.Videoapi.hanzo.ai/v1/video](https://hanzo.ai/koma) [Iroiro-1Research previewHigh-fidelity image generation, creative direction, editing, character design and consistent visual assets.Imageapi.hanzo.ai/v1/images](https://hanzo.ai/iro) [Morimori-1Research preview3D assets, geometry, materials, environments and spatially consistent scenes.3Dapi.hanzo.ai/v1/3d](https://hanzo.ai/mori) [Otooto-1Research previewFilm Foley, immersive sound effects, environmental audio and synchronized scene sound.Foleyapi.hanzo.ai/v1/foley](https://hanzo.ai/oto) [Koekoe-1Research previewDirectable speech synthesis, character performances, dubbing and multilingual dialogue.Voiceapi.hanzo.ai/v1/audio/speech](https://hanzo.ai/koe) [Utauta-1Research previewSoundtracks, original songs, musical ideas, cue-driven scoring and creative music production.Musicapi.hanzo.ai/v1/music](https://hanzo.ai/uta) [Make something in Studio →](https://hanzo.ai/studio) ## Flagships from other labs [Claude Fable 5anthropic/claude-fable-51MClaude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...text](https://hanzo.ai/models/anthropic/claude-fable-5) [GPT-3.5 Turbo (older v0613)openai/gpt-3.5-turbo-06134KGPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.text](https://hanzo.ai/models/openai/gpt-3.5-turbo-0613) [Gemini 2.5 Progoogle/gemini-2.5-pro1MGemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...text](https://hanzo.ai/models/google/gemini-2.5-pro) [DeepSeek V3deepseek/deepseek-chat164KDeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...text](https://hanzo.ai/models/deepseek/deepseek-chat) [Grok 4.20x-ai/grok-4.202MGrok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...text](https://hanzo.ai/models/x-ai/grok-4.20) [Muse Glimmer 30Bmeta/muse-glimmer-30b131KMuse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...text](https://hanzo.ai/models/meta/muse-glimmer-30b) [Command Acohere/command-a256KCommand A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...text](https://hanzo.ai/models/cohere/command-a) [Every model, priced →](#catalog) ## Every model, and what it costs Dollars per million tokens, in and out, from the live catalog. Reading every model and its rate from api.hanzo.ai [How models are called and billed →](https://docs.hanzo.ai/docs/models) ## Try any model Test any model directly on the gateway. Switch models by changing one string. Sign in to chat with Enso, Zen, or any model on the endpoint. Pick a model, start a thread, billed to your account and kept private. [Get free API key](https://platform.hanzo.ai/api-keys)[Open Hanzo Chat](https://hanzo.ai/chat) ## Your first request The chat-completions shape you already send, at api.hanzo.ai/v1, in the language you write. cURL Python TypeScript Go cURL ``` curl https://api.hanzo.ai/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $HANZO_API_KEY" \ -d '{ "model": "enso", "messages": [{"role": "user", "content": "Hello!"}] }' ``` Python ``` from openai import OpenAI client = OpenAI( api_key=os.environ["HANZO_API_KEY"], base_url="https://api.hanzo.ai/v1" ) response = client.chat.completions.create( model="enso", messages=[{"role": "user", "content": "Hello!"}] ) print(response.choices[0].message.content) ``` TypeScript ``` import OpenAI from 'openai' const client = new OpenAI({ apiKey: process.env.HANZO_API_KEY, baseURL: 'https://api.hanzo.ai/v1' }) const response = await client.chat.completions.create({ model: 'enso', messages: [{ role: 'user', content: 'Hello!' }] }) console.log(response.choices[0].message.content) ``` Go ``` package main import ( "context" "fmt" "os" "github.com/sashabaranov/go-openai" ) func main() { cfg := openai.DefaultConfig(os.Getenv("HANZO_API_KEY")) cfg.BaseURL = "https://api.hanzo.ai/v1" client := openai.NewClientWithConfig(cfg) resp, _ := client.CreateChatCompletion(context.Background(), openai.ChatCompletionRequest{ Model: "enso", Messages: []openai.ChatCompletionMessage{ {Role: openai.ChatMessageRoleUser, Content: "Hello!"}, }, }, ) fmt.Println(resp.Choices[0].Message.Content) } ``` [Get an API key →](https://platform.hanzo.ai/api-keys)[The quickstart →](https://docs.hanzo.ai/docs/quickstart) Related capabilities [AgentsBuild & run agents](https://hanzo.ai/agents)[Inference](https://hanzo.ai/engine)[EmbeddingsTurn anything into vectors](https://hanzo.ai/cloud/embeddings)