enso and Zen, on one endpoint
enso is our frontier family. Zen is our open-weight family — call it here or run the weights yourself. Models from other labs answer on the same endpoint when you need one.
Our models
enso is our frontier family; Zen is our open-weight family, with the weights published. Both are trained here and served here.
Zen model: enso
Zen model: enso-flash
Zen model: enso-ultra
Next-generation agentic frontier model with native chain-of-thought.
High-throughput agentic model for demanding production workloads.
Zen model: zen5-coder
Zen model: zen5-flash
Open-weight vision-language model.
Zen model: zen-image
Open-weight embedding model.
Browse by lab
Every model on the endpoint, grouped by who trained it.
Models from other labs
Routed on the same endpoint, with the same key, when a workflow needs a specific one.
This model always redirects to the latest model in the DeepSeek V4 Flash family.
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...
Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...
Fast-mode variant of [Opus 5](/anthropic/claude-opus-5) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...
Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...
Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...
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" }]
}'