AI model support

Hezo is bring-your-own-model. You connect your own provider accounts, Hezo stores the credentials encrypted (see Master key & encryption), and your agents run on the models you choose.

Supported providers

Each provider is driven through a first-party agentic command-line runtime inside the agent's container - not a lowest-common-denominator wrapper. Anthropic, OpenAI, Google, and xAI each use their own CLI (xAI runs on its Grok Build CLI, on the grok-4.5 model); Kimi, DeepSeek, and Z.ai run through Claude Code against their Anthropic-compatible endpoints; OpenRouter runs through the OpenCode CLI; and Ollama and LM Studio run through Claude Code against your own machine.

Two ways to run Kimi

Moonshot's models are available through either of two entries in the provider list, and you can add both:

• Kimi runs them through Claude Code, pointed at Moonshot's Anthropic-compatible endpoint.
• Kimi Code runs them through Kimi Code, Moonshot's own command-line agent.

They use the same account, the same API key and the same models - only the harness differs. Neither replaces the other, so if you already run Kimi, adding Kimi Code changes nothing about your existing setup. Pick between them per agent (in the agent's settings) or per task (by pinning the task's runtime); otherwise whichever provider you have marked as default is used.

Local models

You can run agents entirely on your own hardware, with no per-token cost and no prompt or code leaving your machine. Hezo supports two local model servers:

Both serve Anthropic's Messages API directly, so agents run on the same Claude Code runtime the hosted Anthropic-compatible providers use. There is nothing to translate and no extra proxy to run.

To connect one, pick it in Add AI provider and fill in the Server URL. Leave the API key blank - Ollama ignores it, and LM Studio only checks one if you turned on Require Authentication.

Use an address the agents can reach

This is the one thing that catches people out. Agents run inside a container, so localhost there means the container itself, not the machine running your model server. A URL that works in your browser will fail at run time.

Use one of these instead:

• http://host.docker.internal:11434 - a server on the same machine as Hezo.
• http://192.168.1.50:11434 - a server elsewhere on your network, by its LAN address.

Hezo warns you in the connect form if you enter a localhost address.

Cost and model choice

Local runs record $0, because nothing is billed per token. That is a real zero, not a missing price - but it does mean budgets do not constrain local agents, since there is no spend to cap.

Pick a model with strong tool-calling ability. Agents work by calling tools in a loop, and smaller local models are noticeably weaker at it than the hosted frontier models. Some capabilities the hosted providers offer are also unavailable locally, including prompt caching and token counting.

API key or subscription

Most providers accept either a plain API key or, where supported, a subscription sign-in (for example Claude Pro/Max, ChatGPT, or Gemini) - so you can put an existing plan to work instead of paying per token. You choose the method when you connect the provider.

Where to get an API key

Each provider issues API keys from its own console. When you connect a provider, the form in Hezo walks you through these same steps inline.

Most consoles show a newly created key only once - copy it right away and paste it into Hezo, which stores it encrypted. Providers billed per token generally need a positive balance before agents can run. The local servers need no key at all - you give them a server URL instead.

Use more than one

You can connect several providers at once and keep them all available. That's useful for spreading work across accounts, keeping a cheaper model on hand for routine tasks and a frontier model for the hard ones, or simply having a fallback.

When a key is stored it's checked against the provider and shown as verified (the Verify action re-checks it any time). Mark one provider as the default with the star: that's the single global default every agent uses unless it has its own model override. Change the default and agents on the default pick up the new provider on their next run.

Give an agent its own model

By default the agents on a team share the team's model, but you can override the model for any individual agent. One agent can run on Claude while another on the same team runs on Gemini or DeepSeek - whatever fits its job. Set it when you hire the agent or any time afterward from its settings. See Hiring & customizing agents.

Wherever you pick a specific model - a provider's default model, or an agent's override - Hezo loads the list of choices live from that provider, so you always see the models your key can actually use. Providers you signed in to with a subscription instead of an API key use the model their CLI selects, so there's no list to choose from there.