Escalate hard decisions with the advisor tool

The advisor tool is experimental and requires the Anthropic API. It is not available on Amazon Bedrock, Claude Platform on AWS, Google Cloud’s Agent Platform, or Microsoft Foundry. Behavior, pricing, and availability may change.

server tool, available to both subscription and API-billed accounts. You choose which model acts as the advisor, and Claude decides when to call it. This page covers how to enable the advisor, which model pairings are accepted, what Claude shows during a consultation, and how advisor usage is billed.

When to use the advisor #

The advisor fits long, multi-step tasks where most turns are routine but plan quality determines the outcome. Examples include large refactors, debugging sessions where an error keeps recurring, and tasks you want independently checked before Claude declares them done. It adds less value on short tasks where there is little to plan, or on work where every turn needs the strongest model. For those,

[switch the main model](https://code.claude.com/docs/en/model-config#setting-your-model)instead, or see

[how the advisor compares with opusplan and subagents](#compare-with-related-features)for other ways to get a second opinion.

Enable the advisor #

You can set the advisor model in three ways:

• /advisor command : set or change the advisor mid-session and save it as your default

- **`advisorModel` setting** : configure a persistent default in your[settings file](https://code.claude.com/docs/en/settings)
- **`--advisor` flag** : set the advisor for a single session at launch

[supports it](#choose-an-advisor-model). After the session starts, Claude Code shows an

Advisor Tool (experimental) is on and may use more tokens · /advisor notification. To stop using the advisor, see Turn the advisor off. On some plans, Fable as the advisor also needs your one-time

[consent to bill Fable usage to usage credits](https://code.claude.com/docs/en/model-config#fable-and-usage-credits). For what happens before you have given that consent, see

[Fable advisor and usage credits](#fable-advisor-and-usage-credits).

Use the /advisor command

Run /advisor without arguments to open a picker listing the available advisor models, or pass the model directly: Advisor set to followed by the advisor model name. Your selection is saved to advisorModel in your user settings and persists across sessions, except in the cases the lists as applying to the current session only. The command also works where there is no terminal picker: in

advisorModel entry

non-interactive modewith -p, in the Agent SDK, in the desktop app, and over Remote Control. This requires Claude Code v2.1.260 or later. On those surfaces:

• Run /advisor with no argument to print the current advisor model and the aliases it accepts.
• Run /advisor with a model, such as/advisor opus , to set it.
• Run /advisor off to turn it off.

allowlist excludes. To use the advisor, pick an allowed model with availableModels``/advisor. Claude Code still saves an advisor that your current main model doesn’t support. That advisor activates after you switch to a compatible main modelwith

. If the API already refused the saved advisor in the current conversation, it stays off until

/model``/clear or /compact, even after you switch models.

On some plans, Fable as the advisor also needs your one-time [consent to bill Fable usage to usage credits](https://code.claude.com/docs/en/model-config#fable-and-usage-credits). For what

`/advisor fable` does before you have given that consent, see [Fable advisor and usage credits](#fable-advisor-and-usage-credits).

Set advisorModel in settings

To configure the advisor as a default without opening a session, set it in your settings file:

Use the --advisor flag

To set the advisor for a single session without changing your saved setting, launch with the flag: advisorModel setting for that session. It doesn’t list --advisor in claude --help. Claude Code exits with an error at launch if:

• The session’s main model doesn’t support the advisor
• The requested model, such as Haiku, can’t act as an advisor

- Your organization’s [`availableModels`](https://code.claude.com/docs/en/model-config#restrict-model-selection) allowlist excludes the requested model
- You requested Fable and your account still requires the [usage-credits consent](#fable-advisor-and-usage-credits)

[background session](https://code.claude.com/docs/en/agent-view)with

--advisor and one of these applies, Claude Code starts the session without the advisor instead of exiting.

Choose an advisor model #

The advisor must be at least as capable as the main model. The accepted advisors for each main model are: Fable 5.1 requires Claude Code v2.1.257 or later. Both Fable models require

Fable access. Set the advisor as fable, opus, or sonnet. These aliases resolve to Claude Code’s built-in default version for each model family, which advances with new Claude Code releases. You can also pass a full model ID such as claude-opus-5-5. Subagents inherit the configured advisor and apply the same pairing check against their own model. Claude Code validates the pairing before sending a request, and the API validates it again:

• For an advisor the table lists as rejected, Claude Code doesn’t attach it to the main model’s requests. The /advisor command output and a notification show this. Subagents whose own model satisfies the pairing may still use the advisor.
• For an advisor the table lists as refused by the API, Claude Code attaches it and the API refuses it. Claude Code then resends that request without the advisor, and the rest of the conversation runs without one, so you see no error and get no advisor calls. Pick an accepted advisor with /advisor ; the change takes effect after/clear or/compact and in new sessions.
• If the main model or the advisor is a model Claude Code does not recognize, the advisor is not attached.

Fable advisor and usage credits

On some plans, Fable usage bills to usage credits, and Fable as the advisor bills the same way. If your account requires the

one-time consent to bill Fable usage to usage credits, Claude Code asks for it when you select a Fable model with /model and doesn’t apply Fable as the advisor until you have accepted that consent. Before you have accepted it, Claude Code doesn’t save Fable as the advisor when you type /advisor fable or pick Fable in the /advisor picker. It points you to /model fable instead. With claude --advisor fable, Claude Code exits at launch with a message that points to /model fable. In a background session, it starts the session without the advisor instead of exiting. With Fable already saved as your

advisorModel, Claude Code sends requests without the advisor. In an interactive session whose main model supports the advisor, it also shows a notification that points to /model fable. To accept the consent, run /model fable and choose to continue on Fable. Claude Code records the consent and saves Fable as your selected model. Then select Fable as the advisor.

Common model pairings

Any accepted pairing works. These combinations balance cost against capability in different ways:

When Claude consults the advisor #

Claude decides when to call the advisor. It tends to consult before committing to an approach, when an error keeps recurring, and before declaring a task done, but the timing is model-driven rather than rule-based. You can ask for a consultation in your prompt the same way you would request any tool, for exampleconsult the advisor before you continue. There is no setting to cap or force advisor calls; if you want Claude to consult more or less often during a task, say so in your instructions.

What you see during a session #

When Claude calls the advisor, the transcript shows anAdvising line with the advisor model name while the call is in progress. When the result returns, the line reports whether the advisor gave guidance:

• Reviewed : the line confirms that the advisor has reviewed the conversation. When the advisor returned readable guidance, pressCtrl+O to read it.
• Declined : the line readsAdvisor declined to advise on this request . If the advisor gave a reason, pressCtrl+O to read it.
• Unavailable : the advisor call failed, and the line readsAdvisor unavailable (<error_code>) , where<error_code> is the code the call returned.

how the advisor compares with subagents and opusplan.

Cost #

When Claude calls the advisor, the advisor model reads the conversation, so each call consumes tokens at the advisor model’s rates in addition to your main model’s usage. How those advisor tokens are billed depends on how you pay:

• API billing : you pay the advisor model’s input and output rates for advisor tokens
• Subscription plans : advisor usage counts toward your plan’s usage limits, except that a Fable advisor bills tousage credits on plans where Fable usage does

doesn’t apply the selectionuntil then. Claude calls the advisor at decision points rather than on every turn, so pairing a faster main model with a stronger advisor typically costs less than running the stronger model throughout. Advisor usage counts toward the session totals shown by

. For how advisor tokens are reported in API responses, see /usage

Usage and billingin the Claude API documentation.

Impact on prompt caching #

Enabling or disabling the advisor mid-session does not invalidate your main model’s

[prompt cache](https://code.claude.com/docs/en/prompt-caching). Unlike

[switching models](https://code.claude.com/docs/en/prompt-caching#switching-models), toggling

/advisor keeps the cached prefix intact, and the advisor’s returned guidance is cached as part of the transcript on later turns. The advisor model’s own read of the conversation is not cached. Each advisor call processes the full transcript anew, with no reuse between calls.

Requirements #

The advisor tool requires all of the following:

• Anthropic API only : the advisor is a server-executed tool. It is not available on Amazon Bedrock, Claude Platform on AWS, Google Cloud’s Agent Platform, or Microsoft Foundry. Through anLLM gateway configured withANTHROPIC_BASE_URL , availability depends on whether the gateway forwards the request intact to the Anthropic API. If the gateway or its upstream doesn’t recognize the advisor tool, seeAutomatic retry and error forwarding for how Claude Code responds.
• Supported main model : Fable, Opus 4.6 or later, Sonnet 4.6 or later, or Haiku 4.5. SeeChoose an advisor model for which advisors each accepts.
• Feature-flag fetching : Claude Code turns the advisor on through a feature flag it fetches from Anthropic. In a session where a variable that turns flag fetching off is set, such asDISABLE_TELEMETRY , the advisor stays off. SeeFeatures that need feature-flag fetching .

Turn the advisor off #

To stop using the advisor, run/advisor off or choose No advisor in the

/advisor picker: CLAUDE_CODE_DISABLE_ADVISOR_TOOL=1. The /advisor command becomes unavailable and any configured advisorModel is ignored. The --advisor flag is accepted but has no effect. See Environment variables.

Compare with related features #

The advisor is one of several ways to combine model strengths. Pick based on when you want a second model involved.

See also #

- [Model configuration](https://code.claude.com/docs/en/model-config) : switch models, set effort levels, and use`opusplan`
- [Manage costs effectively](https://code.claude.com/docs/en/costs) : track token usage across models
- [Advisor tool in the Claude API](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool) : understand the underlying server tool, or use it directly from the Messages API
- [The advisor strategy](https://claude.com/blog/the-advisor-strategy) : why pairing a fast main model with a stronger advisor works

source & further reading

code.claude.com — original article