Skip to main content
Every task runs one coding agent. Aether ships three selectable agent providers — Codex (the default), Claude Code, and OpenCode — each with its own curated model catalog and reasoning options. You pick the agent, model, interaction mode, and reasoning effort per task, and you can save those choices as project or account defaults.

The Three Agents

The platform default agent is codex with interaction_mode: default. Claude Code and Codex tasks run on Aether inference or a held connection; OpenCode needs a held connection. See Agent connections for each option and the default connection rules.

Codex

OpenAI Codex: GPT-6 Sol supports low, medium, high, xhigh, max, and ultra reasoning effort. GPT-6.1 Sol and GPT-6 Luna support the same set up to max.

Claude Code

Anthropic Claude Code. Four models: Every model accepts the full reasoning-effort range — low, medium, high, xhigh, max, ultrathink, ultracode. The default effort is xhigh.

OpenCode

OpenCode routes to a curated catalog of models across providers (OpenRouter, OpenCode Zen, Anthropic). The catalog includes Claude, GPT, Gemini, DeepSeek, Mimo, Kimi, Qwen, and GLM model variants; the default is opencode-claude-sonnet-4-6. Which models you can actually run depends on the credentials in your uploaded auth file and the provider’s entitlements — selecting a model your bridge can’t reach fails loudly. OpenRouter-routed OpenCode models can use a bring-your-own OpenRouter key.

Interaction Mode

Interaction mode controls how the agent starts work:

Selecting Per Task

Pass the agent, model, interaction mode, and reasoning effort when you create a task. Unset fields fall back to the project defaults.
Open the task composer and use its settings menu to pick the agent, model, interaction mode, and reasoning effort before sending the prompt.

Changing a Task’s Settings

aether task update changes the model, interaction mode, and reasoning effort on an existing task. Its harness stays fixed. Only the flags you pass are changed.
When you send a follow-up, you can override the interaction mode and reasoning effort for that turn:

Setting Defaults

A new task inherits the agent, model, interaction mode, and reasoning effort from its project’s task defaults. Update them once and every new task in that project starts from those settings.
Set defaults in Settings → Projects → Task defaults, or save the current composer settings as the project default from the composer’s settings menu.

OpenRouter BYOK for OpenCode

OpenCode models routed through OpenRouter can use your own OpenRouter API key. Add it as a named connection and choose it as your default for OpenCode tasks in Settings → Connections, or choose it in a task’s Runs on setting.
This OpenRouter key is only used for OpenCode’s OpenRouter-routed models. Codex and Claude Code authenticate through their own provider connections — see Agent connections.

Next Steps

Agent connections

Authenticate Codex, Claude Code, and OpenCode.

Tasks

Create, watch, and respond to agent runs.