Files

352 lines
11 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.
[
[
{
"h1": "Frontier AI families"
},
{
"p": "Proprietary and open weight models for text, decisions, video, image, and more — one account, one API key."
},
{
"a": "Get API key",
"href": "https://platform.hanzo.ai/api-keys"
},
{
"a": "Every model",
"href": "#catalog"
},
{
"button": "Enso"
},
{
"button": "Zen 6"
},
{
"button": "Claude Fable 5"
},
{
"p": "Hanzo's proprietary frontier model — Opus-class reasoning by default with 1M-context overflow."
}
],
[
{
"p": "Three families"
},
{
"h2": "Enso routes. Kai decides. Zen reasons."
},
{
"li": "routes Enso Picks the model for every call, in every modality. Explore Enso →",
"href": "/enso"
},
{
"li": "decides Kai Answers a choice, a score or a yes/no, with the probability of each. 11 · Suites won · Kai vs Jev Explore Kai →",
"href": "/kai"
},
{
"li": "reasons Zen Open weights for the code, the copy, the images and the voice. Zen 6 and Zen 6 Flash now · Zen 7 in research preview Explore Zen →",
"href": "/zen"
}
],
[
{
"p": "Enso vs Zen"
},
{
"h2": "Proprietary orchestration, on open foundations"
},
{
"h3": "Enso"
},
{
"li": "Flash, Pro and Ultra presets"
},
{
"li": "OpenAI- and Anthropic-compatible"
},
{
"li": "Metered and audited per organization"
},
{
"a": "Explore Enso →",
"href": "/enso"
},
{
"h3": "Zen"
},
{
"li": "Free to download and self-host"
},
{
"li": "Or call it on Hanzo Cloud"
},
{
"li": "From a 501(c)(3) non-profit"
},
{
"a": "Explore Zen →",
"href": "/zen"
}
],
[
{
"h2": "Enso models"
},
{
"a": "Enso enso 900K Hanzo's proprietary frontier model — Opus-class reasoning by default with 1M-context overflow. text",
"href": "/models/hanzo/enso"
},
{
"a": "Enso Flash enso-flash 900K Fast, economical Enso tier for high-volume, low-latency everyday work, with 1M-context overflow. text",
"href": "/models/hanzo/enso-flash"
},
{
"a": "Enso Ultra enso-ultra 1M Adaptive fan-out — probes a task-appropriate model, escalates to a top-K panel only when needed, then verifies-then-selects the best answer. text",
"href": "/models/hanzo/enso-ultra"
},
{
"a": "Enso: the router, its presets and its runs →",
"href": "/enso"
}
],
[
{
"h2": "Zen models"
},
{
"p": "Open weights, made with Zoo Labs Foundation . Download every Zen model at huggingface.co/zenlm , or call it here."
},
{
"a": "Zoo Labs Foundation",
"href": "https://zoo.ngo"
},
{
"a": "huggingface.co/zenlm",
"href": "https://huggingface.co/zenlm"
},
{
"a": "Zen6 zen6 1M text",
"href": "/models/hanzo/zen6"
},
{
"a": "Zen6 Flash zen6-flash 1M text",
"href": "/models/hanzo/zen6-flash"
},
{
"a": "Zen5 (Default) zen5 1M Canonical 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",
"href": "/models/hanzo/zen5"
},
{
"a": "Zen5 Pro zen5-pro 1M Zen 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",
"href": "/models/hanzo/zen5-pro"
},
{
"a": "Zen5 Coder zen5-coder 1M Code-specialized Zen5 tier. 80B sparse MoE tuned for repo-scale code understanding, agentic refactoring, and tool-use coding loops. text",
"href": "/models/hanzo/zen5-coder"
},
{
"a": "Zen5 Flash zen5-flash 1M Smallest and cheapest text-only Zen5 chat tier. 4B-class dense, sub-100ms TTFT, 32K context. For high-volume routing and simple agent loops. text",
"href": "/models/hanzo/zen5-flash"
},
{
"a": "Zen VL — Vision-Language zen-vl 1M Reads images and reasons over them — visual Q&A, document and chart understanding, grounded captioning. text",
"href": "/models/hanzo/zen-vl"
},
{
"a": "Zen Embedding zen-embedding 33K Dense text embeddings for semantic search, retrieval, and clustering. embeddings",
"href": "/models/hanzo/zen-embedding"
},
{
"p": "The next open-weight generation after Zen 6, in research preview."
},
{
"a": "Request access",
"href": "/zen/7"
},
{
"a": "Run Zen: the docs →",
"href": "https://docs.hanzo.ai/docs/models/zen"
}
],
[
{
"h2": "Kai decision models"
},
{
"a": "Kai kai 33K Hanzo 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-2 target. Text State Vision (Kai-2 target)",
"href": "/models/hanzo/kai"
},
{
"a": "Decision Benchmarks 11 suites won vs jev Ahead 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",
"href": "/kai#benchmarks"
},
{
"a": "Autonomous Agent Steering decision-ready A choice, a score or a yes/no, each with its probabilities, for agent loops such as Hanzo Dev's. choice score noul",
"href": "/kai#types"
},
{
"a": "Kai: decisions and their benchmarks →",
"href": "/kai"
}
],
[
{
"h2": "Creative models"
},
{
"p": "Video, images, 3D, sound effects, voice and music, each its own model, in research preview."
},
{
"a": "Koma koma-1 Research preview Cinematic video generation, character continuity, motion, animation, and shot-level creative control. Video api.hanzo.ai/v1/video",
"href": "/koma"
},
{
"a": "Iro iro-1 Research preview High-fidelity image generation, creative direction, editing, character design and consistent visual assets. Image api.hanzo.ai/v1/images",
"href": "/iro"
},
{
"a": "Mori mori-1 Research preview 3D assets, geometry, materials, environments and spatially consistent scenes. 3D api.hanzo.ai/v1/3d",
"href": "/mori"
},
{
"a": "Oto oto-1 Research preview Film Foley, immersive sound effects, environmental audio and synchronized scene sound. Foley api.hanzo.ai/v1/foley",
"href": "/oto"
},
{
"a": "Koe koe-1 Research preview Directable speech synthesis, character performances, dubbing and multilingual dialogue. Voice api.hanzo.ai/v1/audio/speech",
"href": "/koe"
},
{
"a": "Uta uta-1 Research preview Soundtracks, original songs, musical ideas, cue-driven scoring and creative music production. Music api.hanzo.ai/v1/music",
"href": "/uta"
},
{
"a": "Make something in Design →",
"href": "/design"
}
],
[
{
"h2": "Flagships from other labs"
},
{
"a": "Claude Fable 5 anthropic/claude-fable-5 1M Claude 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",
"href": "/models/anthropic/claude-fable-5"
},
{
"a": "GPT-3.5 Turbo (older v0613) openai/gpt-3.5-turbo-0613 4K GPT-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.\n\nTraining data up to Sep 2021. text",
"href": "/models/openai/gpt-3.5-turbo-0613"
},
{
"a": "Gemini 2.5 Pro google/gemini-2.5-pro 1M Gemini 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",
"href": "/models/google/gemini-2.5-pro"
},
{
"a": "DeepSeek V3 deepseek/deepseek-chat 164K DeepSeek-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",
"href": "/models/deepseek/deepseek-chat"
},
{
"a": "Grok 4.20 x-ai/grok-4.20 2M Grok 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",
"href": "/models/x-ai/grok-4.20"
},
{
"a": "Muse Glimmer 30B meta/muse-glimmer-30b 131K Muse 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",
"href": "/models/meta/muse-glimmer-30b"
},
{
"a": "Command A cohere/command-a 256K Command 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",
"href": "/models/cohere/command-a"
},
{
"a": "Every model, priced →",
"href": "#catalog"
}
],
[
{
"h2": "Every model, and what it costs"
},
{
"p": "Dollars per million tokens, in and out, from the live catalog."
},
{
"a": "How models are called and billed →",
"href": "https://docs.hanzo.ai/docs/models"
}
],
[
{
"h2": "Try any model"
},
{
"p": "Test any model directly on the gateway. Switch models by changing one string."
},
{
"p": "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."
},
{
"a": "Get free API key",
"href": "https://platform.hanzo.ai/api-keys"
},
{
"a": "Open Hanzo Chat",
"href": "/chat"
}
],
[
{
"h2": "Your first request"
},
{
"p": "The chat-completions shape you already send, at api.hanzo.ai/v1, in the language you write."
},
{
"button": "cURL"
},
{
"button": "Python"
},
{
"button": "TypeScript"
},
{
"button": "Go"
},
{
"code": "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!\"}] } '"
},
{
"code": "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 )"
},
{
"code": "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 )"
},
{
"code": "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 ) }"
},
{
"a": "Get an API key →",
"href": "https://platform.hanzo.ai/api-keys"
},
{
"a": "The quickstart →",
"href": "https://docs.hanzo.ai/docs/quickstart"
}
],
[
{
"p": "Related capabilities"
},
{
"a": "Agents Build & run agents",
"href": "/agents"
},
{
"a": "Inference",
"href": "/engine"
},
{
"a": "Embeddings Turn anything into vectors",
"href": "/cloud/embeddings"
}
]
]