Claude Code
How Conductor runs Claude Code and how Claude Code usage is billed
Conductor runs Claude Code through the Claude Code setup available to Conductor. That can be Conductor's bundled Claude Code binary, your system Claude Code binary if configured, and the Claude Code authentication or provider environment available in Conductor.
Claude Code
Anthropic's coding agent running inside a Conductor workspace.
Models
Use the provider docs for the live model list and pricing.
| Model | Guidance |
|---|---|
| Opus 4.8 | Newest Opus option listed in Anthropic's Claude Code model configuration. Availability depends on your Claude Code account, subscription, API key, and provider setup. |
| Opus 4.7 | Versioned Opus option for deeper reasoning and harder coding tasks. Use the /model or /status commands in Claude Code to confirm whether your account exposes it. |
| Sonnet 4.6 | Current Sonnet option listed in Anthropic's Claude Code model configuration. Anthropic describes Sonnet as the practical default for most coding work. |
| Opus 4.6 | Versioned Opus option available in Claude Code where your setup supports it. Opus uses more quota than Sonnet; switch when deeper reasoning is worth the cost. |
| Opus 4.5 | Dated Opus 4.5 model identifier published for Claude Code configuration. Anthropic publishes claude-opus-4-5-20251101 for environment-variable configuration. |
| Haiku 4.5 | Fast, lower-cost Claude option for quick mechanical work. Anthropic recommends Haiku for simple edits, lookups, boilerplate, and high-volume scripted runs. |
| Sonnet 4.5 | Dated Sonnet 4.5 model identifier published for Claude Code configuration. Keep this as a versioned option only when your Claude Code setup exposes it. |
Capabilities and controls
These notes describe how Conductor wraps the harness and where provider controls still apply.
Auth path decides billing
ANTHROPIC_API_KEY can move Claude Code from subscription usage to API billing.
Conductor owns the workspace
The branch, terminal, diff, checks, and PR state stay in Conductor while Claude Code writes code.
Controls depend on setup
Plan Mode, Fast Mode, checkpoints, and skills appear when the selected Claude Code setup supports them.
When to use Claude Code
Use Claude Code when you want Anthropic's coding agent inside a Conductor workspace. It fits implementation, debugging, review, and long-running tasks that should stay attached to a branch, terminal, diff, checks, and pull request path.
Claude Code can use Conductor session controls such as Plan Mode, Fast Mode, effort controls, checkpoints, and skills when those controls are supported by the selected model and Claude Code setup. For the full control matrix, see Agent modes.
Setup
Conductor uses the Claude Code authentication available to the app. Check auth status in Settings -> Providers.
Claude Code can authenticate through:
- a Claude Pro or Max subscription connected to Claude Code
- Claude Console or Anthropic API billing
- supported third-party or cloud providers configured through environment variables
Configure provider environment variables in Settings -> Environment. For examples, see Configure model providers.
Usage and billing
Conductor does not bill or meter Claude Code usage. Claude Code usage is controlled by the Claude account, subscription, API credits, provider, and environment variables used by Claude Code.
Anthropic documents Claude Code access through Pro and Max plans, with usage shared across Claude and Claude Code. Anthropic also documents API credit usage as a separate billing path at API rates.
If ANTHROPIC_API_KEY is set in Conductor or in the shell environment that
launches Conductor, Claude Code may use that API key instead of Claude
subscription usage. That can result in API charges.
Use /status inside Claude Code to inspect the active Claude Code account and remaining allocation when available. Review Anthropic's billing and plan docs before switching between subscription and API-credit usage.