Skip to content

Latest commit

 

History

History
302 lines (242 loc) · 18.4 KB

File metadata and controls

302 lines (242 loc) · 18.4 KB
title Feature availability
source https://code.claude.com/docs/en/feature-availability
category code
generated true

Documentation Index

Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt Use this file to discover all available pages before exploring further.

Feature availability

Compare which Claude Code features are available across Anthropic subscription plans, the Anthropic Console, Amazon Bedrock, Claude Platform on AWS, Google Vertex AI, and Microsoft Foundry.

The Claude Code CLI and everything that runs locally work identically on every provider. For setup instructions per provider, see the Enterprise deployment overview. To skip straight to what is missing on your provider, see the summary by provider tabs.

In the tables below, ✓ means available, ✗ means not available, and "See note" links to a footnote for partial support. A qualifier after ✓ narrows availability to that subset, and "Admin-enabled" means the feature is off until an organization admin turns it on.

Availability by model provider

How you authenticate determines which features Claude Code can reach. For a single list of what is missing on your provider, see the summary by provider tabs. To find your column in the tables:

  • Claude subscription: you sign in with a claude.ai account on the Pro, Max, Team, or Enterprise plan
  • Anthropic Console: you authenticate with an Anthropic API key
  • Amazon Bedrock: you use Claude models from the Bedrock model catalog and set CLAUDE_CODE_USE_BEDROCK. The Mantle endpoint (CLAUDE_CODE_USE_MANTLE) is covered by this column
  • Claude Platform on AWS: you bought Claude through AWS Marketplace but call the Anthropic API, and set CLAUDE_CODE_USE_ANTHROPIC_AWS
  • Google Vertex AI: Google-operated; you set CLAUDE_CODE_USE_VERTEX
  • Microsoft Foundry: Anthropic-operated on Azure; you set CLAUDE_CODE_USE_FOUNDRY

Features available on every provider

These work identically on every provider:

Features that require a Claude subscription

These require signing in with a claude.ai account and are not reachable with an Anthropic Console API key or from a third-party provider:

Desktop is the partial exception: Enterprise deployments can route Desktop to Vertex AI or a gateway provider via managed settings, and the Cowork on 3P research preview runs the Code tab on Bedrock, Vertex AI, Foundry, or a self-hosted LLM gateway. For per-plan availability of these features, see Availability by subscription plan.

CLI capabilities that vary by provider

These features work in the local CLI but depend on a server-side capability that not every provider exposes.

<tr>
  <td>[Fast mode](./code-fast-mode.md)</td>
  <td>✓</td>
  <td>✓</td>
  <td>✗</td>
  <td>✗</td>
  <td>✗</td>
  <td>✗</td>
</tr>

<tr>
  <td>[Auto mode](./code-auto-mode-config.md)</td>
  <td>✓</td>
  <td>✓</td>
  <td>See note <sup><a href="#fn2">2</a></sup></td>
  <td>✓</td>
  <td>See note <sup><a href="#fn2">2</a></sup></td>
  <td>See note <sup><a href="#fn2">2</a></sup></td>
</tr>

<tr>
  <td>[Advisor](./code-advisor.md)</td>
  <td>✓</td>
  <td>✓</td>
  <td>✗</td>
  <td>✗</td>
  <td>✗</td>
  <td>✗</td>
</tr>

<tr>
  <td>[Channels](./code-channels.md)</td>
  <td>✓</td>
  <td>✓</td>
  <td>✗</td>
  <td>✗</td>
  <td>✗</td>
  <td>✗</td>
</tr>

<tr>
  <td>[`/loop` scheduled tasks](./code-scheduled-tasks.md)</td>
  <td>✓</td>
  <td>✓</td>
  <td>See note <sup><a href="#fn3">3</a></sup></td>
  <td>✓</td>
  <td>See note <sup><a href="#fn3">3</a></sup></td>
  <td>See note <sup><a href="#fn3">3</a></sup></td>
</tr>

<tr>
  <td>[GitHub Actions](./code-github-actions.md) and [GitLab CI/CD](./code-gitlab-ci-cd.md)</td>
  <td>✓</td>
  <td>✓</td>
  <td>✓</td>
  <td>✓</td>
  <td>✓</td>
  <td>✗</td>
</tr>
Feature Claude subscription Anthropic Console Amazon Bedrock Claude Platform on AWS Google Vertex AI Microsoft Foundry
[Web search](./code-tools-reference.md#websearch-tool-behavior) See note 1

Admin and analytics

Organization-level controls and usage visibility.

<tr>
  <td>[Server-managed settings](./code-server-managed-settings.md)</td>
  <td>✓ (Team and Enterprise)</td>
  <td>✓ (Team and Enterprise)</td>
  <td>✗</td>
  <td>✗</td>
  <td>✗</td>
  <td>✗</td>
</tr>

<tr>
  <td>[Zero Data Retention](./code-zero-data-retention.md)</td>
  <td>✓ (qualified Enterprise accounts)</td>
  <td>✓ (qualified accounts)</td>
  <td>See note <sup><a href="#fn4">4</a></sup></td>
  <td>✓ (qualified accounts)</td>
  <td>See note <sup><a href="#fn4">4</a></sup></td>
  <td>See note <sup><a href="#fn4">4</a></sup></td>
</tr>
Feature Claude subscription Anthropic Console Amazon Bedrock Claude Platform on AWS Google Vertex AI Microsoft Foundry
[Analytics dashboard and API](./code-analytics.md) ✓ (Team and Enterprise) 5

<span id="fn1" style={{display: 'block', position: 'relative', top: '-120px'}} />1 On Vertex AI, web search is available for Claude 4 models and later.
<span id="fn2" style={{display: 'block', position: 'relative', top: '-120px'}} />2 Requires CLAUDE_CODE_ENABLE_AUTO_MODE. See Auto mode configuration.
<span id="fn3" style={{display: 'block', position: 'relative', top: '-120px'}} />3 Explicit intervals such as /loop every 2 hours work on every provider. On Bedrock, Vertex AI, and Foundry, /loop cannot pick its own interval or supply the default maintenance prompt, so a prompt with no interval runs every 10 minutes, and /loop with no arguments shows the usage message. See Scheduled tasks.
<span id="fn4" style={{display: 'block', position: 'relative', top: '-120px'}} />4 Subject to your agreement with the cloud provider.
<span id="fn5" style={{display: 'block', position: 'relative', top: '-120px'}} />5 Dashboard and API only. Contribution metrics requires a claude.ai Team or Enterprise organization.

If you authenticate through an [LLM gateway](./code-llm-gateway.md), feature availability matches the underlying provider the gateway forwards to. Some Anthropic-only features such as the [Advisor](./code-advisor.md) work only if the gateway forwards requests intact to the Anthropic API.

Summary by provider

Each tab lists what is unavailable or partially supported on that provider, with alternatives where one exists. Everything not listed works the same as on a Claude subscription. On Bedrock, Vertex AI, Foundry, and Claude Platform on AWS, error reporting and telemetry to Anthropic are off by default. See default behaviors by API provider for what traffic still reaches Anthropic and how to opt out.

**Not available:** all [features that require a Claude subscription](#features-that-require-a-claude-subscription), plus [web search](./code-tools-reference.md#websearch-tool-behavior), [fast mode](./code-fast-mode.md), [Advisor](./code-advisor.md), [Channels](./code-channels.md), the [analytics dashboard](./code-analytics.md), and [server-managed settings](./code-server-managed-settings.md).
**Partial support:**

* [Desktop](./code-desktop.md): only via the [Cowork on 3P research preview](https://claude.com/docs/cowork/3p/overview)
* [Auto mode](./code-auto-mode-config.md): set `CLAUDE_CODE_ENABLE_AUTO_MODE`
* [`/loop`](./code-scheduled-tasks.md): explicit intervals only
* [Zero Data Retention](./code-zero-data-retention.md): subject to your AWS agreement

**Alternatives:** for scheduling, use [`/loop`](./code-scheduled-tasks.md) with an explicit interval instead of `/schedule`. For cloud sessions, use [GitHub Actions](./code-github-actions.md) or [GitLab CI/CD](./code-gitlab-ci-cd.md). For web lookups, use the [WebFetch tool](./code-tools-reference.md#webfetch-tool-behavior) with a specific URL.
**Not available:** all [features that require a Claude subscription](#features-that-require-a-claude-subscription), plus [fast mode](./code-fast-mode.md), [Advisor](./code-advisor.md), [Channels](./code-channels.md), the [analytics dashboard](./code-analytics.md), and [server-managed settings](./code-server-managed-settings.md).
**Available** where Bedrock is not: [web search](./code-tools-reference.md#websearch-tool-behavior), [auto mode](./code-auto-mode-config.md) without an opt-in flag, and [`/loop` self-pacing](./code-scheduled-tasks.md).

**Alternatives:** for scheduling, use [`/loop`](./code-scheduled-tasks.md) instead of `/schedule`. For cloud sessions, use [GitHub Actions](./code-github-actions.md) or [GitLab CI/CD](./code-gitlab-ci-cd.md).
**Not available:** all [features that require a Claude subscription](#features-that-require-a-claude-subscription), plus [fast mode](./code-fast-mode.md), [Advisor](./code-advisor.md), [Channels](./code-channels.md), the [analytics dashboard](./code-analytics.md), and [server-managed settings](./code-server-managed-settings.md).
**Partial support:**

* [Desktop](./code-desktop.md): via [managed settings](https://support.claude.com/en/articles/12622667-enterprise-configuration) or the [Cowork on 3P research preview](https://claude.com/docs/cowork/3p/overview)
* [Web search](./code-tools-reference.md#websearch-tool-behavior): Claude 4 models and later
* [Auto mode](./code-auto-mode-config.md): set `CLAUDE_CODE_ENABLE_AUTO_MODE`
* [`/loop`](./code-scheduled-tasks.md): explicit intervals only
* [Zero Data Retention](./code-zero-data-retention.md): subject to your Google Cloud agreement

**Alternatives:** for scheduling, use [`/loop`](./code-scheduled-tasks.md) with an explicit interval instead of `/schedule`. For cloud sessions, use [GitHub Actions](./code-github-actions.md) or [GitLab CI/CD](./code-gitlab-ci-cd.md).
**Not available:** all [features that require a Claude subscription](#features-that-require-a-claude-subscription), plus [fast mode](./code-fast-mode.md), [Advisor](./code-advisor.md), [Channels](./code-channels.md), [GitHub Actions](./code-github-actions.md) and [GitLab CI/CD](./code-gitlab-ci-cd.md), the [analytics dashboard](./code-analytics.md), and [server-managed settings](./code-server-managed-settings.md).
**Partial support:**

* [Desktop](./code-desktop.md): only via the [Cowork on 3P research preview](https://claude.com/docs/cowork/3p/overview)
* [Auto mode](./code-auto-mode-config.md): set `CLAUDE_CODE_ENABLE_AUTO_MODE`
* [`/loop`](./code-scheduled-tasks.md): explicit intervals only
* [Zero Data Retention](./code-zero-data-retention.md): subject to your Azure agreement

**Alternatives:** for scheduling, use [`/loop`](./code-scheduled-tasks.md) with an explicit interval instead of `/schedule`.
**Not available:** all [features that require a Claude subscription](#features-that-require-a-claude-subscription).
Everything in [CLI capabilities that vary by provider](#cli-capabilities-that-vary-by-provider) is available, as are [server-managed settings](./code-server-managed-settings.md) when the API key belongs to a Team or Enterprise organization.

Availability by subscription plan

If you authenticate through Bedrock, Vertex AI, Foundry, or an Anthropic Console API key, this section does not apply to you. When you sign in with a claude.ai account, your plan determines which of the features below are available.

Feature Pro Max Team Enterprise
Claude Code on the web 6
Routines
Remote Control Admin-enabled Admin-enabled
Channels Admin-enabled Admin-enabled
Computer use
Dispatch (Desktop)
Code Review
Artifacts Admin-enabled
Analytics dashboard, API, and contribution metrics
Server-managed settings
SSO
SCIM
Compliance API
Zero Data Retention 7

<span id="fn6" style={{display: 'block', position: 'relative', top: '-120px'}} />6 On Enterprise, requires a premium seat or a Chat + Claude Code seat. See Claude Code on the web.
<span id="fn7" style={{display: 'block', position: 'relative', top: '-120px'}} />7 Not included in the standard Enterprise plan. Requires separate enablement by Anthropic for qualified accounts. See Zero Data Retention.

For pricing and the full plan comparison, see Team plans and Enterprise plans.

Model availability

For which Claude models and context-window sizes are available per provider and region, see Model configuration and the Models overview. Vision, PDF input, and extended thinking are model capabilities rather than Claude Code features and work on every provider that offers the model. Prompt caching works the same way on most providers; on Bedrock, support varies by model.

Related resources