100 <th>Anthropic Console</th>100 <th>Anthropic Console</th>
101 <th>Amazon Bedrock</th>101 <th>Amazon Bedrock</th>
102 <th>Claude Platform on AWS</th>102 <th>Claude Platform on AWS</th>
103 <th>Google Vertex AI</th>103 <th>Google Cloud's Agent Platform, formerly Vertex AI</th>
104 <th>Microsoft Foundry</th>104 <th>Microsoft Foundry</th>
105 </tr>105 </tr>
106 </thead>106 </thead>
194 194
195* [Claude for Teams or Enterprise](/en/authentication#claude-for-teams-or-enterprise)195* [Claude for Teams or Enterprise](/en/authentication#claude-for-teams-or-enterprise)
196* [Anthropic Console](/en/authentication#claude-console-authentication)196* [Anthropic Console](/en/authentication#claude-console-authentication)
197* [Claude apps gateway](/en/claude-apps-gateway), a self-hosted gateway that adds IdP sign-in in front of Amazon Bedrock, Claude Platform on AWS, Google Vertex AI, Microsoft Foundry, or the Anthropic API197* [Claude apps gateway](/en/claude-apps-gateway), a self-hosted gateway that adds IdP sign-in in front of Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, Microsoft Foundry, or the Anthropic API
198* [Amazon Bedrock](/en/amazon-bedrock)198* [Amazon Bedrock](/en/amazon-bedrock)
199* [Claude Platform on AWS](/en/claude-platform-on-aws)199* [Claude Platform on AWS](/en/claude-platform-on-aws)
200* [Google Vertex AI](/en/google-vertex-ai)200* [Google Cloud's Agent Platform](/en/google-vertex-ai)
201* [Microsoft Foundry](/en/microsoft-foundry)201* [Microsoft Foundry](/en/microsoft-foundry)
202 202
203## Configure proxies and gateways203## Configure proxies and gateways
213 213
214<Tabs>214<Tabs>
215 <Tab title="Corporate proxy">215 <Tab title="Corporate proxy">
216 Route Bedrock traffic through your corporate proxy by setting the following [environment variables](/en/env-vars):216 Route Amazon Bedrock traffic through your corporate proxy by setting the following [environment variables](/en/env-vars):
217 217
218 ```bash theme={null}218 ```bash theme={null}
219 # Enable Bedrock219 # Enable Bedrock
226 </Tab>226 </Tab>
227 227
228 <Tab title="LLM Gateway">228 <Tab title="LLM Gateway">
229 Route Bedrock traffic through your LLM gateway by setting the following [environment variables](/en/env-vars):229 Route Amazon Bedrock traffic through your LLM gateway by setting the following [environment variables](/en/env-vars):
230 230
231 ```bash theme={null}231 ```bash theme={null}
232 # Enable Bedrock232 # Enable Bedrock
243 243
244<Tabs>244<Tabs>
245 <Tab title="Corporate proxy">245 <Tab title="Corporate proxy">
246 Route Foundry traffic through your corporate proxy by setting the following [environment variables](/en/env-vars):246 Route Microsoft Foundry traffic through your corporate proxy by setting the following [environment variables](/en/env-vars):
247 247
248 ```bash theme={null}248 ```bash theme={null}
249 # Enable Microsoft Foundry249 # Enable Microsoft Foundry
257 </Tab>257 </Tab>
258 258
259 <Tab title="LLM Gateway">259 <Tab title="LLM Gateway">
260 Route Foundry traffic through your LLM gateway by setting the following [environment variables](/en/env-vars):260 Route Microsoft Foundry traffic through your LLM gateway by setting the following [environment variables](/en/env-vars):
261 261
262 ```bash theme={null}262 ```bash theme={null}
263 # Enable Microsoft Foundry263 # Enable Microsoft Foundry
270 </Tab>270 </Tab>
271</Tabs>271</Tabs>
272 272
273### Google Vertex AI273### Google Cloud's Agent Platform
274 274
275<Tabs>275<Tabs>
276 <Tab title="Corporate proxy">276 <Tab title="Corporate proxy">
277 Route Vertex AI traffic through your corporate proxy by setting the following [environment variables](/en/env-vars):277 Route Google Cloud's Agent Platform traffic through your corporate proxy by setting the following [environment variables](/en/env-vars):
278 278
279 ```bash theme={null}279 ```bash theme={null}
280 # Enable Vertex280 # Enable Agent Platform
281 export CLAUDE_CODE_USE_VERTEX=1281 export CLAUDE_CODE_USE_VERTEX=1
282 export CLOUD_ML_REGION=us-east5282 export CLOUD_ML_REGION=us-east5
283 export ANTHROPIC_VERTEX_PROJECT_ID=your-project-id283 export ANTHROPIC_VERTEX_PROJECT_ID=your-project-id
288 </Tab>288 </Tab>
289 289
290 <Tab title="LLM Gateway">290 <Tab title="LLM Gateway">
291 Route Vertex AI traffic through your LLM gateway by setting the following [environment variables](/en/env-vars):291 Route Google Cloud's Agent Platform traffic through your LLM gateway by setting the following [environment variables](/en/env-vars):
292 292
293 ```bash theme={null}293 ```bash theme={null}
294 # Enable Vertex294 # Enable Agent Platform
295 export CLAUDE_CODE_USE_VERTEX=1295 export CLAUDE_CODE_USE_VERTEX=1
296 296
297 # Configure LLM gateway297 # Configure LLM gateway
328 328
329### Pin model versions for cloud providers329### Pin model versions for cloud providers
330 330
331If you deploy through [Bedrock](/en/amazon-bedrock), [Vertex AI](/en/google-vertex-ai), [Foundry](/en/microsoft-foundry), or [Claude Platform on AWS](/en/claude-platform-on-aws), pin specific model versions using `ANTHROPIC_DEFAULT_FABLE_MODEL`, `ANTHROPIC_DEFAULT_OPUS_MODEL`, `ANTHROPIC_DEFAULT_SONNET_MODEL`, and `ANTHROPIC_DEFAULT_HAIKU_MODEL`. Without pinning, model aliases resolve to Claude Code's built-in default for that provider, which can lag the newest release and may not yet be enabled in your account. Pinning lets you control when your users move to a new model. See [Model configuration](/en/model-config#pin-models-for-third-party-deployments) for what each provider does when the default is unavailable.331If you deploy through [Amazon Bedrock](/en/amazon-bedrock), [Google Cloud's Agent Platform](/en/google-vertex-ai), [Microsoft Foundry](/en/microsoft-foundry), or [Claude Platform on AWS](/en/claude-platform-on-aws), pin specific model versions using `ANTHROPIC_DEFAULT_FABLE_MODEL`, `ANTHROPIC_DEFAULT_OPUS_MODEL`, `ANTHROPIC_DEFAULT_SONNET_MODEL`, and `ANTHROPIC_DEFAULT_HAIKU_MODEL`. Without pinning, model aliases resolve to Claude Code's built-in default for that provider, which can lag the newest release and may not yet be enabled in your account. Pinning lets you control when your users move to a new model. See [Model configuration](/en/model-config#pin-models-for-third-party-deployments) for what each provider does when the default is unavailable.
332 332
333### Configure security policies333### Configure security policies
334 334
