# Hanzo Models via Hanzo AI — 30 models > Access 30 Hanzo models via Hanzo's OpenAI-compatible API. Single API key, unified billing, and global low-latency routing. [Models](https://hanzo.ai/models)/Hanzo # Hanzo Models via Hanzo AI 30 models available Access all 30 Hanzo models through Hanzo's OpenAI-compatible API. One key, one bill, no rate limit juggling. [Get API Access](https://hanzo.ai/signup)[API Docs](https://docs.hanzo.ai) Instant Guest API Keyguest_temp_key No account or sign up required Test right now from your terminal. No credentials needed: cURL · instant guest request Copy ``` curl https://api.hanzo.ai/v1/chat/completions \ -H "Authorization: Bearer guest_temp_key" \ -d '{"model": "zen-free", "messages": [{"role": "user", "content": "hello"}]}' ``` [Enso900KHanzo's proprietary frontier model — Opus-class reasoning by default with 1M-context overflow.text](https://hanzo.ai/models/hanzo/enso) [Enso (enso-auto)900KRoutes each request to one tier by the reasoning depth it asks for: enso-flash at off, none, minimal, low, default; enso-pro at medium, high; enso-ultra at xhigh, max. It bills at the price of the tier that answers; the price shown is a request's that states no depth. When nothing pays for that tier it answers on enso-free, at no charge, and says so.text](https://hanzo.ai/models/hanzo/enso-auto) [Enso Flash900KFast, economical Enso tier for high-volume, low-latency everyday work, with 1M-context overflow.text](https://hanzo.ai/models/hanzo/enso-flash) [enso-free1Mtext](https://hanzo.ai/models/hanzo/enso-free) [enso-pro1Mtext](https://hanzo.ai/models/hanzo/enso-pro) [Enso 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) [free66Ktext](https://hanzo.ai/models/hanzo/free) [Kai33KHanzo 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) [hanzo/zen1Mtext](https://hanzo.ai/models/hanzo/zen) [Kai (kai-1.8)33KHanzo 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-1.8) [komaimage](https://hanzo.ai/models/hanzo/koma) [Zen Embedding33KDense text embeddings for semantic search, retrieval, and clustering.embeddings](https://hanzo.ai/models/hanzo/zen-embedding) [zen-embedding-333Kembeddings](https://hanzo.ai/models/hanzo/zen-embedding-3) [zen-free1Mtext](https://hanzo.ai/models/hanzo/zen-free) [Zen Guard — Content Safety128KSafety classifier for moderation and guardrails across a broad category and language set.text](https://hanzo.ai/models/hanzo/zen-guard) [zen-scribeHanzo's speech-to-text model, which writes down what is said in any language, served at /v1/audio/transcriptions.transcript](https://hanzo.ai/models/hanzo/zen-scribe) [Zen VL — Vision-Language1MReads images and reasons over them — visual Q&A, document and chart understanding, grounded captioning.text](https://hanzo.ai/models/hanzo/zen-vl) [zen-voice-miniHanzo's text-to-speech voice, served at /v1/audio/speech.audio](https://hanzo.ai/models/hanzo/zen-voice-mini) [Zen5 (Default)1MCanonical 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 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-evo1Mtext](https://hanzo.ai/models/hanzo/zen5-evo) [Zen5 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) [Zen5 Mini1MFrontier agentic at the lowest cost in the family. Built on a 230B agentic MoE (10B active) (230B MoE / 10B active, released Feb 2026). 80.2% SWE-Bench Verified, 76.3% BrowseComp; trained on 200K+ real-world environments via large-scale RL.text](https://hanzo.ai/models/hanzo/zen5-mini) [Zen5 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-spark1Mtext](https://hanzo.ai/models/hanzo/zen5-spark) [zen61Mtext](https://hanzo.ai/models/hanzo/zen6) [zen6-coder1Mtext](https://hanzo.ai/models/hanzo/zen6-coder) [zen6-flash1Mtext](https://hanzo.ai/models/hanzo/zen6-flash) [zen6-free1Mtext](https://hanzo.ai/models/hanzo/zen6-free) [zen6-max1Mtext](https://hanzo.ai/models/hanzo/zen6-max) ## Use Hanzo models via Hanzo One key. One bill. Works with every SDK you already have. [Start Free](https://platform.hanzo.ai/api-keys)[Browse All Models](https://hanzo.ai/models)