Every model, one endpoint
Enso is our frontier family, and it answers here only. Zen is Zoo Labs Foundation’s open-weight family — call it here, or download the weights and run it yourself. Every other lab answers on the same address, under the same key.
Enso
Our frontier family, trained by Hanzo and served at this address only.
Zen
The open-weight family from Zoo Labs Foundation. We serve it first-party — and the weights are published, so you can run it yourself and never call us at all.
Next-generation agentic frontier model with native chain-of-thought.
High-throughput agentic model for demanding production workloads.
Open-weight vision-language model.
Open-weight embedding model.
Top models
One flagship per lab, so you can find the name you already know. They answer at the same address with the same key, and switching to one is changing a string.
Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results here #multimodal
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 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 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...
Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.
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 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...
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...
Browse by lab
Every model on the endpoint, grouped by who trained it. Prices and context windows come from the live catalog, so what you read here is what you will be billed.
Try it
Pick any model and start a thread — the same chat that runs at hanzo.chat, signed in with your Hanzo account.
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.
One key, one host
Changing model is changing one string. The endpoint takes and returns the chat-completions JSON shape, so an HTTP client already written against that shape works once its base URL points at api.hanzo.ai/v1.
curl https://api.hanzo.ai/v1/chat/completions \
-H "Authorization: Bearer $HANZO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "zen5",
"messages": [{ "role": "user", "content": "Hello" }]
}'