---
title: "llm-anthropic 0.26 Released: Adds Claude 5 Models and Server-Side Tool Support"
source: "Simon Willison 博客（Atom）"
source_tier: "t2"
url: "https://simonwillison.net/2026/Aug/4/llm-anthropic/#atom-everything"
permalink: "https://feed.astralor.com/items/itm_dace681f7641d31c02df7d66"
published: "2026-08-04T22:00:58.000Z"
score: 73
channel: "ai"
tags: ["Agent Tools","Anthropic","Claude 5","llm-anthropic","LLM CLI","MCP"]
---

# llm-anthropic 0.26 Released: Adds Claude 5 Models and Server-Side Tool Support

## AI commentary

> The most notable part of this update is server-side tools becoming first-class citizens, signaling Anthropic pushing Agent capabilities down to API and CLI layers. For developers building automation pipelines or complex toolchains, the default thinking mechanism of Claude 5 will change latency and output patterns, so early testing is advisable.

## At a glance

llm-anthropic 0.26 is released, leveraging LLM 0.32 to add Claude Fable 5, Sonnet 5, and Opus 5 models, along with server-side tools such as WebSearch, WebFetch, CodeExecution, and AnthropicMCP, callable via LLM's -T interface or Python tools=. Legacy -o web_search* options are removed in favor of -T WebSearch. Reasoning, tool calls, and results now stream as typed events, with CLI reasoning displayed on stderr unless hidden via -R. Claude 5 models think by default, with thinking_effort control, and Fable 5 always thinks. The update simplifies extended thinking configuration and improves the model integration experience.

## Key points

- Adds three models: claude-fable-5, claude-sonnet-5, and claude-opus-5.
- Adds server-side tools WebSearch, WebFetch, CodeExecution, and AnthropicMCP, usable via -T or Python tools=.
- Reasoning, tool calls, and results stream as typed events; CLI reasoning defaults to stderr and can be hidden with -R.
- Claude 5 models think by default, supporting thinking_effort low/medium/high/xhigh/max; Fable 5 always thinks.

## Full text

Release: llm-anthropic 0.26 Includes new features enabled by LLM 0.32: New models: claude-fable-5, claude-sonnet-5, and claude-opus-5. #75, #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 Upgraded to llm>=0.32. 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 Tags: llm, anthropic, claude, model-context-protocol

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_dace681f7641d31c02df7d66