Files

1 line
10 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":["Models","Frontier AI families","Proprietary and open weight models for text, decisions, video, image, and more — one account, one API key.","Get API key","Every model","Live from api.hanzo.ai","POST /v1/chat/completions","example","Enso","Zen 6","Claude Fable 5","{ \"model\":",", \"messages\": [{ \"role\": \"user\", \"content\": \"Who are you?\" }] }","\"enso\"","Hanzo's proprietary frontier model — Opus-class reasoning by default with 1M-context overflow.","900K","text","Three families","Enso routes. Kai decides. Zen reasons.","routes","Picks the model for every call, in every modality.","Explore Enso →","decides","Kai","Answers a choice, a score or a yes/no, with the probability of each.","11","Suites won · Kai vs Jev","Explore Kai →","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 →","Enso vs Zen","Proprietary orchestration, on open foundations","Proprietary · Hanzo Cloud only","Flash, Pro and Ultra presets","OpenAI- and Anthropic-compatible","Metered and audited per organization","Open weights · Zoo Labs Foundation","Free to download and self-host","Or call it on Hanzo Cloud","From a 501(c)(3) non-profit","Enso models","enso","Enso Flash","enso-flash","Fast, economical Enso tier for high-volume, low-latency everyday work, with 1M-context overflow.","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.","Enso: the router, its presets and its runs","Zen models","Open weights, made with",". Download every Zen model at",", or call it here.","Zoo Labs Foundation","huggingface.co/zenlm","Zen6","zen6","Zen6 Flash","zen6-flash","Zen5 (Default)","zen5","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.","Zen5 Pro","zen5-pro","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.","Zen5 Coder","zen5-coder","Code-specialized Zen5 tier. 80B sparse MoE tuned for repo-scale code understanding, agentic refactoring, and tool-use coding loops.","Zen5 Flash","zen5-flash","Smallest and cheapest text-only Zen5 chat tier. 4B-class dense, sub-100ms TTFT, 32K context. For high-volume routing and simple agent loops.","Zen VL — Vision-Language","zen-vl","Reads images and reasons over them — visual Q&A, document and chart understanding, grounded captioning.","Zen Embedding","zen-embedding","33K","Dense text embeddings for semantic search, retrieval, and clustering.","embeddings","Zen 7","zen7","The next open-weight generation after Zen 6, in research preview.","Research preview","Request access","Run Zen: the docs","Kai decision models","kai","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)","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","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","Kai: decisions and their benchmarks","Creative models","Video, images, 3D, sound effects, voice and music, each its own model, in research preview.","Koma","koma-1","Cinematic video generation, character continuity, motion, animation, and shot-level creative control.","Video","api.hanzo.ai/v1/video","Iro","iro-1","High-fidelity image generation, creative direction, editing, character design and consistent visual assets.","Image","api.hanzo.ai/v1/images","Mori","mori-1","3D assets, geometry, materials, environments and spatially consistent scenes.","3D","api.hanzo.ai/v1/3d","Oto","oto-1","Film Foley, immersive sound effects, environmental audio and synchronized scene sound.","Foley","api.hanzo.ai/v1/foley","Koe","koe-1","Directable speech synthesis, character performances, dubbing and multilingual dialogue.","Voice","api.hanzo.ai/v1/audio/speech","Uta","uta-1","Soundtracks, original songs, musical ideas, cue-driven scoring and creative music production.","Music","api.hanzo.ai/v1/music","Make something in Design","Flagships from other labs","anthropic/claude-fable-5","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...","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. Training data up to Sep 2021.","Gemini 2.5 Pro","google/gemini-2.5-pro","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...","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...","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...","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...","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...","Every model, priced","Every model, and what it costs","Dollars per million tokens, in and out, from the live catalog.","Everything","Ours","Free","Under $1 / M out","1M context","27 models.","Model","In $/M","Out $/M","Context","Hanzo","27 models","$0.330","$1.65","enso-auto","Enso Free","enso-free","Enso Pro","enso-pro","$4.40","$22.00","$5.50","$27.50","$0.010","Zen Embedding 3","zen-embedding-3","Zen Free","zen-free","Zen Guard — Content Safety","zen-guard","128K","Zen Scribe","zen-scribe","Zen Voice Mini","zen-voice-mini","Zen5 Evo","zen5-evo","Zen5 Mini","zen5-mini","Zen5 Spark","zen5-spark","Zen6 Coder","zen6-coder","Zen6 Free","zen6-free","Zen6 Max","zen6-max","hanzo/zen","$0.021","How models are called and billed","Try any model","Test any model directly on the gateway. Switch models by changing one string.","Log in","Sign up for free","Sign up","High","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","https://api.hanzo.ai/v1/chat/completions","-H","Content-Type: application/json","Authorization: Bearer","HANZO_API_KEY","-d","\"model\": \"enso\",","\"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}]","from","openai","import","OpenAI","client = OpenAI","api_key=os","environ","],","base_url=","https://api.hanzo.ai/v1","response = client","chat","completions","create","model=","messages=","[{","role","user","content","Hello!","}]","print","response","choices","].","message","const","client = new","({","apiKey","process.env.HANZO_API_KEY","baseURL","})","response =","await","client.chat.completions.","model","messages","console.","log","response.choices",".message.content","package","main","context","fmt","os","github.com/sashabaranov/go-openai","func","()","cfg := openai","DefaultConfig","Getenv","))","cfg","BaseURL =","client := openai","NewClientWithConfig","resp","_ := client","CreateChatCompletion","Background","(),","ChatCompletionRequest","Messages","[]","ChatCompletionMessage","Role","ChatMessageRoleUser","Content","},","Println","Choices","Message","Get an API key","The quickstart","Related capabilities","Agents","Build & run agents","Inference","Embeddings","Turn anything into vectors"],"links":["https://platform.hanzo.ai/api-keys","#catalog","/enso","/kai","/zen","/models/hanzo/enso","/models/hanzo/enso-flash","/models/hanzo/enso-ultra","https://zoo.ngo","https://huggingface.co/zenlm","/models/hanzo/zen6","/models/hanzo/zen6-flash","/models/hanzo/zen5","/models/hanzo/zen5-pro","/models/hanzo/zen5-coder","/models/hanzo/zen5-flash","/models/hanzo/zen-vl","/models/hanzo/zen-embedding","/zen/7","https://docs.hanzo.ai/docs/models/zen","/models/hanzo/kai","/kai#benchmarks","/kai#types","/koma","/iro","/mori","/oto","/koe","/uta","/design","/models/anthropic/claude-fable-5","/models/openai/gpt-3.5-turbo-0613","/models/google/gemini-2.5-pro","/models/deepseek/deepseek-chat","/models/x-ai/grok-4.20","/models/meta/muse-glimmer-30b","/models/cohere/command-a","/models/hanzo","/models/hanzo/enso-auto","/models/hanzo/enso-free","/models/hanzo/enso-pro","/models/hanzo/zen-embedding-3","/models/hanzo/zen-free","/models/hanzo/zen-guard","/models/hanzo/zen-scribe","/models/hanzo/zen-voice-mini","/models/hanzo/zen5-evo","/models/hanzo/zen5-mini","/models/hanzo/zen5-spark","/models/hanzo/zen6-coder","/models/hanzo/zen6-free","/models/hanzo/zen6-max","/models/hanzo/zen","https://docs.hanzo.ai/docs/models","https://docs.hanzo.ai/docs/quickstart","/agents","/engine","/cloud/embeddings"]}