SpyBara
Go Premium

Documentation 2025-11-17 03:24 UTC to 2025-11-18 18:02 UTC

10 files changed +181 −24. View all changes and history on the product overview
2025
Thu 27 06:02 Wed 26 00:04 Tue 25 03:22 Mon 24 21:01 Fri 21 00:04 Thu 20 18:02 Wed 19 03:21 Tue 18 18:02 Mon 17 03:24 Sun 16 00:04 Fri 14 21:26 Thu 6 18:02 Tue 4 18:02 Mon 3 21:01 Sun 2 18:01 Sat 1 21:01

azure-ai-foundry.md +107 −0 created

Details

1# Claude Code on Azure AI Foundry

2 

3> Learn about configuring Claude Code through Azure AI Foundry, including setup, configuration, and troubleshooting.

4 

5## Prerequisites

6 

7Before configuring Claude Code with Azure AI Foundry, ensure you have:

8 

9* An Azure subscription with access to Azure AI Foundry

10* RBAC permissions to create Azure AI Foundry resources and deployments

11* Azure CLI installed and configured (optional - only needed if you don’t have another mechanism for getting credentials)

12 

13## Setup

14 

15### 1. Provision Azure AI Foundry resource

16 

17First, create a Claude resource in Azure:

18 

191. Navigate to the [Azure AI Foundry portal](https://ai.azure.com/)

202. Create a new resource, noting your resource name

213. Create deployments for the Claude models:

22 * Claude Opus

23 * Claude Sonnet

24 * Claude Haiku

25 

26### 2. Configure Azure credentials

27 

28Claude Code supports two authentication methods for Azure AI Foundry. Choose the method that best fits your security requirements.

29 

30**Option A: API key authentication**

31 

321. Navigate to your resource in the Azure AI Foundry portal

332. Go to the **Endpoints and keys** section

343. Copy **API Key**

354. Set the environment variable:

36 

37```bash theme={null}

38export ANTHROPIC_FOUNDRY_API_KEY=your-azure-api-key

39```

40 

41**Option B: Microsoft Entra ID authentication**

42 

43When `ANTHROPIC_FOUNDRY_API_KEY` is not set, Claude Code automatically uses the Azure SDK [default credential chain](https://learn.microsoft.com/en-us/azure/developer/javascript/sdk/authentication/credential-chains#defaultazurecredential-overview).

44This supports a variety of methods for authenticating local and remote workloads.

45 

46On local environments, you commonly may use the Azure CLI:

47 

48```bash theme={null}

49az login

50```

51 

52<Note>

53 When using AI Foundry, the `/login` and `/logout` commands are disabled since authentication is handled through Azure credentials.

54</Note>

55 

56### 3. Configure Claude Code

57 

58Set the following environment variables to enable Azure AI Foundry. Note that your deployments' names are set as the model identifiers in Claude Code (may be optional if using suggested deployment names).

59 

60```bash theme={null}

61# Enable Azure AI Foundry integration

62export CLAUDE_CODE_USE_FOUNDRY=1

63 

64# Azure resource name (replace {resource} with your resource name)

65export ANTHROPIC_FOUNDRY_RESOURCE={resource}

66# Or provide the full base URL:

67# export ANTHROPIC_FOUNDRY_BASE_URL=https://{resource}.services.ai.azure.com

68 

69# Set models to your resource's deployment names

70export ANTHROPIC_DEFAULT_SONNET_MODEL='claude-sonnet-4-5'

71export ANTHROPIC_DEFAULT_HAIKU_MODEL='claude-haiku-4-5'

72export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-1'

73```

74 

75For more details on model configuration options, see [Model configuration](/en/model-config).

76 

77## Azure RBAC configuration

78 

79The `Azure AI User` and `Cognitive Services User` default roles include all required permissions for invoking Claude models.

80 

81For more restrictive permissions, create a custom role with the following:

82 

83```json theme={null}

84{

85 "permissions": [

86 {

87 "dataActions": [

88 "Microsoft.CognitiveServices/accounts/providers/*"

89 ]

90 }

91 ]

92}

93```

94 

95For details, see [Azure AI Foundry RBAC documentation](https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/rbac-azure-ai-foundry).

96 

97## Troubleshooting

98 

99If you receive an error "Failed to get token from azureADTokenProvider: ChainedTokenCredential authentication failed":

100 

101* Configure Entra ID on the environment, or set `ANTHROPIC_FOUNDRY_API_KEY`.

102 

103## Additional resources

104 

105* [AI Foundry documentation](https://learn.microsoft.com/en-us/azure/ai-foundry/what-is-azure-ai-foundry)

106* [AI Foundry models](https://ai.azure.com/explore/models)

107* [AI Foundry pricing](https://azure.microsoft.com/en-us/pricing/details/ai-foundry/)

hooks.md +4 −2

Details

474 "tool_input": {474 "tool_input": {

475 "file_path": "/path/to/file.txt",475 "file_path": "/path/to/file.txt",

476 "content": "file content"476 "content": "file content"

477 }477 },

478 "tool_use_id": "toolu_01ABC123..."

478}479}

479```480```

480 481 


497 "tool_response": {498 "tool_response": {

498 "filePath": "/path/to/file.txt",499 "filePath": "/path/to/file.txt",

499 "success": true500 "success": true

500 }501 },

502 "tool_use_id": "toolu_01ABC123..."

501}503}

502```504```

503 505 

iam.md +5 −4

Details

4 4 

5## Authentication methods5## Authentication methods

6 6 

7Setting up Claude Code requires access to Anthropic models. For teams, you can set up Claude Code access in one of three ways:7Setting up Claude Code requires access to Anthropic models. For teams, you can set up Claude Code access in one of four ways:

8 8 

9* Claude API via the Claude Console9* Claude API via the Claude Console

10* Amazon Bedrock10* Amazon Bedrock

11* Azure AI Foundry

11* Google Vertex AI12* Google Vertex AI

12 13 

13### Claude API authentication14### Claude API authentication


29 30 

30### Cloud provider authentication31### Cloud provider authentication

31 32 

32**To set up Claude Code access for your team via Bedrock or Vertex:**33**To set up Claude Code access for your team via Bedrock, Vertex, or Azure:**

33 34 

341. Follow the [Bedrock docs](/en/amazon-bedrock) or [Vertex docs](/en/google-vertex-ai)351. Follow the [Bedrock docs](/en/amazon-bedrock), [Vertex docs](/en/google-vertex-ai), or [Azure AI Foundry docs](/en/azure-ai-foundry)

352. Distribute the environment variables and instructions for generating cloud credentials to your users. Read more about how to [manage configuration here](/en/settings).362. Distribute the environment variables and instructions for generating cloud credentials to your users. Read more about how to [manage configuration here](/en/settings).

363. Users can [install Claude Code](/en/setup#installation)373. Users can [install Claude Code](/en/setup#installation)

37 38 


195Claude Code securely manages your authentication credentials:196Claude Code securely manages your authentication credentials:

196 197 

197* **Storage location**: On macOS, API keys, OAuth tokens, and other credentials are stored in the encrypted macOS Keychain.198* **Storage location**: On macOS, API keys, OAuth tokens, and other credentials are stored in the encrypted macOS Keychain.

198* **Supported authentication types**: Claude.ai credentials, Claude API credentials, Bedrock Auth, and Vertex Auth.199* **Supported authentication types**: Claude.ai credentials, Claude API credentials, Azure Auth, Bedrock Auth, and Vertex Auth.

199* **Custom credential scripts**: The [`apiKeyHelper`](/en/settings#available-settings) setting can be configured to run a shell script that returns an API key.200* **Custom credential scripts**: The [`apiKeyHelper`](/en/settings#available-settings) setting can be configured to run a shell script that returns an API key.

200* **Refresh intervals**: By default, `apiKeyHelper` is called after 5 minutes or on HTTP 401 response. Set `CLAUDE_CODE_API_KEY_HELPER_TTL_MS` environment variable for custom refresh intervals.201* **Refresh intervals**: By default, `apiKeyHelper` is called after 5 minutes or on HTTP 401 response. Set `CLAUDE_CODE_API_KEY_HELPER_TTL_MS` environment variable for custom refresh intervals.

model-config.md +7 −4

Details

4 4 

5## Available models5## Available models

6 6 

7For the `model` setting in Claude Code, you can either configure:7For the `model` setting in Claude Code, you can configure either:

8 8 

9* A **model alias**9* A **model alias**

10* A full **[model name](https://docs.claude.com/en/docs/about-claude/models/overview#model-names)**10* A **model name**

11* For Bedrock, an ARN11 * Anthropic API: A full **[model name](https://docs.claude.com/en/docs/about-claude/models/overview#model-names)**

12 * Bedrock: an inference profile ARN

13 * Foundry: a deployment name

14 * Vertex: a version name

12 15 

13### Model aliases16### Model aliases

14 17 


100## Environment variables103## Environment variables

101 104 

102You can use the following environment variables, which must be full **model105You can use the following environment variables, which must be full **model

103names**, to control the model names that the aliases map to.106names** (or equivalent for your API provider), to control the model names that the aliases map to.

104 107 

105| Env var | Description |108| Env var | Description |

106| -------------------------------- | --------------------------------------------------------------------------------------------- |109| -------------------------------- | --------------------------------------------------------------------------------------------- |

Details

6 6 

7All metrics are time series data exported via OpenTelemetry's standard metrics protocol, and events are exported via OpenTelemetry's logs/events protocol. It is the user's responsibility to ensure their metrics and logs backends are properly configured and that the aggregation granularity meets their monitoring requirements.7All metrics are time series data exported via OpenTelemetry's standard metrics protocol, and events are exported via OpenTelemetry's logs/events protocol. It is the user's responsibility to ensure their metrics and logs backends are properly configured and that the aggregation granularity meets their monitoring requirements.

8 8 

9<Note>

10 OpenTelemetry support is currently in beta and details are subject to change.

11</Note>

12 

13## Quick Start9## Quick Start

14 10 

15Configure OpenTelemetry using environment variables:11Configure OpenTelemetry using environment variables:

settings.md +3 −0

Details

322| `ANTHROPIC_DEFAULT_HAIKU_MODEL` | See [Model configuration](/en/model-config#environment-variables) |322| `ANTHROPIC_DEFAULT_HAIKU_MODEL` | See [Model configuration](/en/model-config#environment-variables) |

323| `ANTHROPIC_DEFAULT_OPUS_MODEL` | See [Model configuration](/en/model-config#environment-variables) |323| `ANTHROPIC_DEFAULT_OPUS_MODEL` | See [Model configuration](/en/model-config#environment-variables) |

324| `ANTHROPIC_DEFAULT_SONNET_MODEL` | See [Model configuration](/en/model-config#environment-variables) |324| `ANTHROPIC_DEFAULT_SONNET_MODEL` | See [Model configuration](/en/model-config#environment-variables) |

325| `ANTHROPIC_FOUNDRY_API_KEY` | API key for Azure AI Foundry authentication (see [Azure AI Foundry](/en/azure-ai-foundry)) |

325| `ANTHROPIC_MODEL` | Name of the model setting to use (see [Model Configuration](/en/model-config#environment-variables)) |326| `ANTHROPIC_MODEL` | Name of the model setting to use (see [Model Configuration](/en/model-config#environment-variables)) |

326| `ANTHROPIC_SMALL_FAST_MODEL` | \[DEPRECATED] Name of [Haiku-class model for background tasks](/en/costs) |327| `ANTHROPIC_SMALL_FAST_MODEL` | \[DEPRECATED] Name of [Haiku-class model for background tasks](/en/costs) |

327| `ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION` | Override AWS region for the Haiku-class model when using Bedrock |328| `ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION` | Override AWS region for the Haiku-class model when using Bedrock |


339| `CLAUDE_CODE_IDE_SKIP_AUTO_INSTALL` | Skip auto-installation of IDE extensions |340| `CLAUDE_CODE_IDE_SKIP_AUTO_INSTALL` | Skip auto-installation of IDE extensions |

340| `CLAUDE_CODE_MAX_OUTPUT_TOKENS` | Set the maximum number of output tokens for most requests |341| `CLAUDE_CODE_MAX_OUTPUT_TOKENS` | Set the maximum number of output tokens for most requests |

341| `CLAUDE_CODE_SKIP_BEDROCK_AUTH` | Skip AWS authentication for Bedrock (e.g. when using an LLM gateway) |342| `CLAUDE_CODE_SKIP_BEDROCK_AUTH` | Skip AWS authentication for Bedrock (e.g. when using an LLM gateway) |

343| `CLAUDE_CODE_SKIP_FOUNDRY_AUTH` | Skip Azure authentication for AI Foundry (e.g. when using an LLM gateway) |

342| `CLAUDE_CODE_SKIP_VERTEX_AUTH` | Skip Google authentication for Vertex (e.g. when using an LLM gateway) |344| `CLAUDE_CODE_SKIP_VERTEX_AUTH` | Skip Google authentication for Vertex (e.g. when using an LLM gateway) |

343| `CLAUDE_CODE_SUBAGENT_MODEL` | See [Model configuration](/en/model-config) |345| `CLAUDE_CODE_SUBAGENT_MODEL` | See [Model configuration](/en/model-config) |

344| `CLAUDE_CODE_USE_BEDROCK` | Use [Bedrock](/en/amazon-bedrock) |346| `CLAUDE_CODE_USE_BEDROCK` | Use [Bedrock](/en/amazon-bedrock) |

347| `CLAUDE_CODE_USE_FOUNDRY` | Use [Azure AI Foundry](/en/azure-ai-foundry) |

345| `CLAUDE_CODE_USE_VERTEX` | Use [Vertex](/en/google-vertex-ai) |348| `CLAUDE_CODE_USE_VERTEX` | Use [Vertex](/en/google-vertex-ai) |

346| `DISABLE_AUTOUPDATER` | Set to `1` to disable automatic updates. |349| `DISABLE_AUTOUPDATER` | Set to `1` to disable automatic updates. |

347| `DISABLE_BUG_COMMAND` | Set to `1` to disable the `/bug` command |350| `DISABLE_BUG_COMMAND` | Set to `1` to disable the `/bug` command |

setup.md +1 −1

Details

70 70 

711. **Claude Console**: The default option. Connect through the Claude Console and complete the OAuth process. Requires active billing at [console.anthropic.com](https://console.anthropic.com). A "Claude Code" workspace will be automatically created for usage tracking and cost management. Note that you cannot create API keys for the Claude Code workspace - it is dedicated exclusively for Claude Code usage.711. **Claude Console**: The default option. Connect through the Claude Console and complete the OAuth process. Requires active billing at [console.anthropic.com](https://console.anthropic.com). A "Claude Code" workspace will be automatically created for usage tracking and cost management. Note that you cannot create API keys for the Claude Code workspace - it is dedicated exclusively for Claude Code usage.

722. **Claude App (with Pro or Max plan)**: Subscribe to Claude's [Pro or Max plan](https://claude.com/pricing) for a unified subscription that includes both Claude Code and the web interface. Get more value at the same price point while managing your account in one place. Log in with your Claude.ai account. During launch, choose the option that matches your subscription type.722. **Claude App (with Pro or Max plan)**: Subscribe to Claude's [Pro or Max plan](https://claude.com/pricing) for a unified subscription that includes both Claude Code and the web interface. Get more value at the same price point while managing your account in one place. Log in with your Claude.ai account. During launch, choose the option that matches your subscription type.

733. **Enterprise platforms**: Configure Claude Code to use [Amazon Bedrock or Google Vertex AI](/en/third-party-integrations) for enterprise deployments with your existing cloud infrastructure.733. **Enterprise platforms**: Configure Claude Code to use [Amazon Bedrock, Google Vertex AI, or Azure AI Foundry](/en/third-party-integrations) for enterprise deployments with your existing cloud infrastructure.

74 74 

75<Note>75<Note>

76 Claude Code securely stores your credentials. See [Credential Management](/en/iam#credential-management) for details.76 Claude Code securely stores your credentials. See [Credential Management](/en/iam#credential-management) for details.

sub-agents.md +5 −1

Details

133description: Description of when this subagent should be invoked133description: Description of when this subagent should be invoked

134tools: tool1, tool2, tool3 # Optional - inherits all tools if omitted134tools: tool1, tool2, tool3 # Optional - inherits all tools if omitted

135model: sonnet # Optional - specify model alias or 'inherit'135model: sonnet # Optional - specify model alias or 'inherit'

136permissionMode: default # Optional - permission mode for the subagent

137skills: skill1, skill2 # Optional - skills to auto-load

136---138---

137 139 

138Your subagent's system prompt goes here. This can be multiple paragraphs140Your subagent's system prompt goes here. This can be multiple paragraphs


146#### Configuration fields148#### Configuration fields

147 149 

148| Field | Required | Description |150| Field | Required | Description |

149| :------------ | :------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |151| :--------------- | :------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

150| `name` | Yes | Unique identifier using lowercase letters and hyphens |152| `name` | Yes | Unique identifier using lowercase letters and hyphens |

151| `description` | Yes | Natural language description of the subagent's purpose |153| `description` | Yes | Natural language description of the subagent's purpose |

152| `tools` | No | Comma-separated list of specific tools. If omitted, inherits all tools from the main thread |154| `tools` | No | Comma-separated list of specific tools. If omitted, inherits all tools from the main thread |

153| `model` | No | Model to use for this subagent. Can be a model alias (`sonnet`, `opus`, `haiku`) or `'inherit'` to use the main conversation's model. If omitted, defaults to the [configured subagent model](/en/model-config) |155| `model` | No | Model to use for this subagent. Can be a model alias (`sonnet`, `opus`, `haiku`) or `'inherit'` to use the main conversation's model. If omitted, defaults to the [configured subagent model](/en/model-config) |

156| `permissionMode` | No | Permission mode for the subagent. Valid values: `default`, `acceptEdits`, `bypassPermissions`, `plan`, `ignore`. Controls how the subagent handles permission requests |

157| `skills` | No | Comma-separated list of skill names to auto-load when the subagent starts. Skills are loaded into the subagent's context automatically |

154 158 

155### Model selection159### Model selection

156 160 

Details

12 <th>Feature</th>12 <th>Feature</th>

13 <th>Anthropic</th>13 <th>Anthropic</th>

14 <th>Amazon Bedrock</th>14 <th>Amazon Bedrock</th>

15 <th>Azure AI Foundry</th>

15 <th>Google Vertex AI</th>16 <th>Google Vertex AI</th>

16 </tr>17 </tr>

17 </thead>18 </thead>


21 <td>Regions</td>22 <td>Regions</td>

22 <td>Supported [countries](https://www.anthropic.com/supported-countries)</td>23 <td>Supported [countries](https://www.anthropic.com/supported-countries)</td>

23 <td>Multiple AWS [regions](https://docs.aws.amazon.com/bedrock/latest/userguide/models-regions.html)</td>24 <td>Multiple AWS [regions](https://docs.aws.amazon.com/bedrock/latest/userguide/models-regions.html)</td>

25 <td>Multiple Azure [regions](https://azure.microsoft.com/en-us/explore/global-infrastructure/products-by-region/)</td>

24 <td>Multiple GCP [regions](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/locations)</td>26 <td>Multiple GCP [regions](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/locations)</td>

25 </tr>27 </tr>

26 28 


29 <td>Enabled by default</td>31 <td>Enabled by default</td>

30 <td>Enabled by default</td>32 <td>Enabled by default</td>

31 <td>Enabled by default</td>33 <td>Enabled by default</td>

34 <td>Enabled by default</td>

32 </tr>35 </tr>

33 36 

34 <tr>37 <tr>

35 <td>Authentication</td>38 <td>Authentication</td>

36 <td>API key</td>39 <td>API key</td>

37 <td>AWS credentials (IAM)</td>40 <td>API key or AWS credentials</td>

38 <td>GCP credentials (OAuth/Service Account)</td>41 <td>API key or Microsoft Entra ID</td>

42 <td>GCP credentials</td>

39 </tr>43 </tr>

40 44 

41 <tr>45 <tr>

42 <td>Cost tracking</td>46 <td>Cost tracking</td>

43 <td>Dashboard</td>47 <td>Dashboard</td>

44 <td>AWS Cost Explorer</td>48 <td>AWS Cost Explorer</td>

49 <td>Azure Cost Management</td>

45 <td>GCP Billing</td>50 <td>GCP Billing</td>

46 </tr>51 </tr>

47 52 


49 <td>Enterprise features</td>54 <td>Enterprise features</td>

50 <td>Teams, usage monitoring</td>55 <td>Teams, usage monitoring</td>

51 <td>IAM policies, CloudTrail</td>56 <td>IAM policies, CloudTrail</td>

57 <td>RBAC policies, Azure Monitor</td>

52 <td>IAM roles, Cloud Audit Logs</td>58 <td>IAM roles, Cloud Audit Logs</td>

53 </tr>59 </tr>

54 </tbody>60 </tbody>


56 62 

57## Cloud providers63## Cloud providers

58 64 

59<CardGroup cols={2}>65<CardGroup cols={3}>

60 <Card title="Amazon Bedrock" icon="aws" href="/en/amazon-bedrock">66 <Card title="Amazon Bedrock" icon="aws" href="/en/amazon-bedrock">

61 Use Claude models through AWS infrastructure with IAM-based authentication and AWS-native monitoring67 Use Claude models through AWS infrastructure with API key or IAM-based authentication and AWS-native monitoring

68 </Card>

69 

70 <Card title="Azure AI Foundry" icon="microsoft" href="/en/azure-ai-foundry">

71 Access Claude through Azure with API key or Microsoft Entra ID authentication and Azure billing

62 </Card>72 </Card>

63 73 

64 <Card title="Google Vertex AI" icon="google" href="/en/google-vertex-ai">74 <Card title="Google Vertex AI" icon="google" href="/en/google-vertex-ai">


117export CLAUDE_CODE_SKIP_BEDROCK_AUTH=1 # If gateway handles AWS auth127export CLAUDE_CODE_SKIP_BEDROCK_AUTH=1 # If gateway handles AWS auth

118```128```

119 129 

130### Using Azure AI Foundry with corporate proxy

131 

132Route Azure traffic through a corporate HTTP/HTTPS proxy:

133 

134```bash theme={null}

135# Enable Azure AI Foundry

136export CLAUDE_CODE_USE_FOUNDRY=1

137export ANTHROPIC_FOUNDRY_RESOURCE=your-resource

138export ANTHROPIC_FOUNDRY_API_KEY=your-api-key # Or omit for Entra ID auth

139 

140# Configure corporate proxy

141export HTTPS_PROXY='https://proxy.example.com:8080'

142```

143 

144### Using Azure AI Foundry with LLM Gateway

145 

146Use a gateway service that provides Azure-compatible endpoints:

147 

148```bash theme={null}

149# Enable Azure AI Foundry

150export CLAUDE_CODE_USE_FOUNDRY=1

151 

152# Configure LLM gateway

153export ANTHROPIC_FOUNDRY_BASE_URL='https://your-llm-gateway.com'

154export CLAUDE_CODE_SKIP_FOUNDRY_AUTH=1 # If gateway handles Azure auth

155```

156 

120### Using Vertex AI with corporate proxy157### Using Vertex AI with corporate proxy

121 158 

122Route Vertex AI traffic through a corporate HTTP/HTTPS proxy:159Route Vertex AI traffic through a corporate HTTP/HTTPS proxy:


216## Next steps253## Next steps

217 254 

218* [Set up Amazon Bedrock](/en/amazon-bedrock) for AWS-native deployment255* [Set up Amazon Bedrock](/en/amazon-bedrock) for AWS-native deployment

256* [Set up Azure AI Foundry](/en/azure-ai-foundry) for Azure deployment

219* [Configure Google Vertex AI](/en/google-vertex-ai) for GCP deployment257* [Configure Google Vertex AI](/en/google-vertex-ai) for GCP deployment

220* [Configure Enterprise Network](/en/network-config) for network requirements258* [Configure Enterprise Network](/en/network-config) for network requirements

221* [Deploy LLM Gateway](/en/llm-gateway) for enterprise management259* [Deploy LLM Gateway](/en/llm-gateway) for enterprise management

vs-code.md +7 −4

Details

414. Review and accept edits directly in the interface414. Review and accept edits directly in the interface

42 * **Tip**: Drag the sidebar wider to see inline diffs, then click on them to expand for full details42 * **Tip**: Drag the sidebar wider to see inline diffs, then click on them to expand for full details

43 43 

44### Using Third-Party Providers (Vertex and Bedrock)44### Using Third-Party Providers

45 45 

46The VS Code extension supports using Claude Code with third-party providers like Amazon Bedrock and Google Vertex AI. When configured with these providers, the extension will not prompt for login. To use third-party providers, configure environment variables in the VS Code extension settings:46The VS Code extension supports using Claude Code with third-party providers like Amazon Bedrock, Azure AI Foundry, and Google Vertex AI. When configured with these providers, the extension will not prompt for login. To use third-party providers, configure environment variables in the VS Code extension settings:

47 47 

481. Open VS Code settings481. Open VS Code settings

492. Search for "Claude Code: Environment Variables"492. Search for "Claude Code: Environment Variables"


52#### Environment Variables52#### Environment Variables

53 53 

54| Variable | Description | Required | Example |54| Variable | Description | Required | Example |

55| :---------------------------- | :------------------------------------- | :--------------------- | :----------------------------------------------- |55| :---------------------------- | :------------------------------------- | :---------------------- | :----------------------------------------------- |

56| `CLAUDE_CODE_USE_BEDROCK` | Enable Amazon Bedrock integration | Required for Bedrock | `"1"` or `"true"` |56| `CLAUDE_CODE_USE_BEDROCK` | Enable Amazon Bedrock integration | Required for Bedrock | `"1"` or `"true"` |

57| `CLAUDE_CODE_USE_FOUNDRY` | Enable Azure AI Foundry integration | Required for Foundry | `"1"` or `"true"` |

57| `CLAUDE_CODE_USE_VERTEX` | Enable Google Vertex AI integration | Required for Vertex AI | `"1"` or `"true"` |58| `CLAUDE_CODE_USE_VERTEX` | Enable Google Vertex AI integration | Required for Vertex AI | `"1"` or `"true"` |

58| `ANTHROPIC_API_KEY` | API key for third-party access | Required | `"your-api-key"` |

59| `AWS_REGION` | AWS region for Bedrock | | `"us-east-2"` |59| `AWS_REGION` | AWS region for Bedrock | | `"us-east-2"` |

60| `AWS_PROFILE` | AWS profile for Bedrock authentication | | `"your-profile"` |60| `AWS_PROFILE` | AWS profile for Bedrock authentication | | `"your-profile"` |

61| `CLOUD_ML_REGION` | Region for Vertex AI | | `"global"` or `"us-east5"` |61| `CLOUD_ML_REGION` | Region for Vertex AI | | `"global"` or `"us-east5"` |

62| `ANTHROPIC_VERTEX_PROJECT_ID` | GCP project ID for Vertex AI | | `"your-project-id"` |62| `ANTHROPIC_VERTEX_PROJECT_ID` | GCP project ID for Vertex AI | | `"your-project-id"` |

63| `ANTHROPIC_FOUNDRY_RESOURCE` | Azure resource name for Foundry | Required for AI Foundry | `"your-resource"` |

64| `ANTHROPIC_FOUNDRY_API_KEY` | API key for Azure AI Foundry | Optional for AI Foundry | `"your-api-key"` |

63| `ANTHROPIC_MODEL` | Override primary model | Override model ID | `"us.anthropic.claude-sonnet-4-5-20250929-v1:0"` |65| `ANTHROPIC_MODEL` | Override primary model | Override model ID | `"us.anthropic.claude-sonnet-4-5-20250929-v1:0"` |

64| `ANTHROPIC_SMALL_FAST_MODEL` | Override small/fast model | Optional | `"us.anthropic.claude-3-5-haiku-20241022-v1:0"` |66| `ANTHROPIC_SMALL_FAST_MODEL` | Override small/fast model | Optional | `"us.anthropic.claude-3-5-haiku-20241022-v1:0"` |

65| `CLAUDE_CODE_SKIP_AUTH_LOGIN` | Disable all prompts to login | Optional | `"1"` or `"true"` |67| `CLAUDE_CODE_SKIP_AUTH_LOGIN` | Disable all prompts to login | Optional | `"1"` or `"true"` |


67For detailed setup instructions and additional configuration options, see:69For detailed setup instructions and additional configuration options, see:

68 70 

69* [Claude Code on Amazon Bedrock](/en/amazon-bedrock)71* [Claude Code on Amazon Bedrock](/en/amazon-bedrock)

72* [Claude Code on Azure AI Foundry](/en/azure-ai-foundry)

70* [Claude Code on Google Vertex AI](/en/google-vertex-ai)73* [Claude Code on Google Vertex AI](/en/google-vertex-ai)

71 74 

72### Not Yet Implemented75### Not Yet Implemented