Models and harnesses

The Model dropdown on the agent node picks both the model and the harness it runs in. The five CLI coding agents are pinned at the top of the list; every other entry runs on the built-in LLM agent. Changing the model on an agent that already has a chat leaves that thread alone until you send. See Changing the model mid-thread. You can also name a model when you ask the AI builder for an agent, for example “a Claude agent that answers support email”, and it sets the Model field to match. The builder does not put a model or vendor name in the agent’s own name or instructions, because that text would go stale the moment you switch models.

​

The six harnesses

The built-in LLM agent runs in-process. The five CLI agents each run in a cloud sandbox that stays warm between turns, so follow-up replies are fast and one agent can hold several conversations at once. A small indicator on the agent node shows how many sandboxes it is currently holding. Sandbox time is billed at 0.05 credits per minute of uptime, even on your own key or subscription. See What costs credits. A sandbox shuts down about a minute after the agent goes idle and starts again on your next message, and it never lives longer than four hours. A turn that stops producing output for 30 minutes is stopped as stalled, and the chat reports it as a lost turn you can send again. See Common errors.

​

Reading the model list

Two tags in the picker tell you what a row actually is: A Free tag is set only from the provider’s own published pricing, so it means the provider charges nothing. Sandbox time for the CLI agents is billed either way.

​

OpenCode Zen and Go models

The opencode/ and opencode-go/ models run on the built-in LLM agent, in-process and without a sandbox, so no sandbox time is billed for them. They are separate from the OpenCode CLI harness, which shares their icon but carries the CLI Agent tag. Both catalogs use one OpenCode key. Connect it in the agent’s Credentials tab; NoClick checks the key when you save it. Zen’s free models then run at no cost to you, and paid ones are billed by OpenCode rather than in NoClick credits.

​

The CLI agents run on your own key

All five CLI agents need an API key or an AI subscription of your own, whichever sub-model you pick. NoClick credits fund the built-in LLM agent’s models and the sandbox time, not the CLI agents’ model usage. Connect the key or subscription in the agent node’s Credentials tab; until you do, the node is marked incomplete on the canvas and its config panel says credentials are required.

​

The key has to match the model

An agent node can hold connected keys for several providers at once. The one that runs is the key belonging to the provider of the model in the Model dropdown, so switching models cannot leave a run using the key for the model you switched away from. When nothing attached matches the selected model, the run behaves as if no key were attached. Models NoClick serves on its own keys still run and are billed in credits, and models that need your own key stop with a missing credential. Connect the matching key in the node’s Credentials tab.

​

Use your existing AI subscription

Instead of API keys or NoClick credits, you can authenticate a harness with the AI subscription you already pay for. Subscription-authenticated runs do not consume NoClick LLM credits; usage counts against your provider plan’s limits. Sandbox time for the CLI agents is still billed (see What costs credits).

​

Claude Code with your Claude account

Works with Claude Pro, Max, Teams, and Enterprise.

​

Codex with your ChatGPT account

Works with ChatGPT Plus and Pro. Requires device code auth enabled in your ChatGPT security settings.

​

GitHub Copilot and xAI SuperGrok (via OpenCode)

Pick OpenCode as the model, then choose a GitHub Copilot or xAI sub-model. The credentials section offers Connect with GitHub Copilot (requires a paid Copilot subscription) or Connect with xAI SuperGrok (requires a SuperGrok subscription). Both use the same device code flow as Codex: a code appears, you enter it on the provider’s verification page, and NoClick completes the connection.

​

Capability matrix

​

Next steps