llm-anthropic 0.26

# Release: llm-anthropic 0.26 Source: [https://simonwillison.net/2026/Aug/4/llm-anthropic/](https://simonwillison.net/2026/Aug/4/llm-anthropic/) Includes new features enabled by[LLM 0\.32](https://simonwillison.net/2026/Aug/4/new-release-of-llm/): > - New models:`claude\-fable\-5`,`claude\-sonnet\-5`, and`claude\-opus\-5`\.[\#75](https://github.com/simonw/llm-anthropic/issues/75),[\#76](https://github.com/simonw/llm-anthropic/issues/76) - Added server\-side tools for`WebSearch`,`WebFetch`,`CodeExecution`, and`AnthropicMCP`, available through LLM's`\-T`interface or Python`tools=`\. The previous`\-o web\_search\*`options have been removed in favor of`\-T WebSearch`\.[\#79](https://github.com/simonw/llm-anthropic/issues/79) - Upgraded to[llm\>=0\.32](https://llm.datasette.io/en/stable/changelog.html#v0-32)\. Reasoning, tool calls, tool results, and server\-side tool results now stream as typed events\. Reasoning for`llm`CLI prompts now displays to standard error unless you pass`\-\-hide\-reasoning/\-R`\. - Simplified extended thinking to`thinking`and`thinking\_effort`\(`low`,`medium`,`high`,`xhigh`, or`max`\)\. Claude 5 models think by default;`\-o thinking 0`disables thinking for Sonnet 5 and Opus 5, while Fable 5 always thinks\.`\-R/\-\-hide\-reasoning`now omits reasoning from responses and logs\. The`thinking\_budget`,`thinking\_display`, and`thinking\_adaptive`options have been removed\.[\#80](https://github.com/simonw/llm-anthropic/issues/80)