Documentation 2026-05-15 22:58 UTC to 2026-05-17 01:01 UTC

173export ENABLE_PROMPT_CACHING_1H=1173export ENABLE_PROMPT_CACHING_1H=1

174```174```

175 175 

176### 5. Run Claude Code

177 

178With the environment variables set, start Claude Code from your project directory:

179 

180```bash theme={null}

181claude

182```

183 

184Claude Code reads `CLAUDE_CODE_USE_FOUNDRY` and the other Foundry variables from the environment and connects to your Azure resource on the first prompt. Unlike Bedrock and Vertex AI, Foundry has no interactive setup wizard, so the environment variables in steps 3 and 4 are the only configuration path.

185 

176## Azure RBAC configuration186## Azure RBAC configuration

177 187 

178The `Azure AI User` and `Cognitive Services User` default roles include all required permissions for invoking Claude models.188The `Azure AI User` and `Cognitive Services User` default roles include all required permissions for invoking Claude models.

207* **In `/model`**: use left/right arrow keys to adjust the effort slider when selecting a model207* **In `/model`**: use left/right arrow keys to adjust the effort slider when selecting a model

208* **`--effort` flag**: pass a level name to set it for a single session when launching Claude Code208* **`--effort` flag**: pass a level name to set it for a single session when launching Claude Code

209* **Environment variable**: set `CLAUDE_CODE_EFFORT_LEVEL` to a level name or `auto`209* **Environment variable**: set `CLAUDE_CODE_EFFORT_LEVEL` to a level name or `auto`

210* **Settings**: set `effortLevel` in your settings file210* **Settings**: set `effortLevel` to `low`, `medium`, `high`, or `xhigh` in your settings file. `max` is [session-only](#adjust-effort-level) and is not accepted here

211* **Skill and subagent frontmatter**: set `effort` in a [skill](/en/skills#frontmatter-reference) or [subagent](/en/sub-agents#supported-frontmatter-fields) markdown file to override the effort level when that skill or subagent runs211* **Skill and subagent frontmatter**: set `effort` in a [skill](/en/skills#frontmatter-reference) or [subagent](/en/sub-agents#supported-frontmatter-fields) markdown file to override the effort level when that skill or subagent runs

212 212 

213The environment variable takes precedence over all other methods, then your configured level, then the model default. Frontmatter effort applies when that skill or subagent is active, overriding the session level but not the environment variable.213The environment variable takes precedence over all other methods, then your configured level, then the model default. Frontmatter effort applies when that skill or subagent is active, overriding the session level but not the environment variable.

407 407 

408This is preprocessing, not something Claude executes. Claude only sees the final result.408This is preprocessing, not something Claude executes. Claude only sees the final result.

409 409 

410Substitution runs once over the original file. Command output is inserted as plain text and is not re-scanned for further `` !`<command>` `` placeholders, so a command cannot emit a placeholder for a later pass to expand.

411 

410For multi-line commands, use a fenced code block opened with ` ```! ` instead of the inline form:412For multi-line commands, use a fenced code block opened with ` ```! ` instead of the inline form:

411 413 

412````markdown theme={null}414````markdown theme={null}