llm-anthropic 0.26 Released: Adds Claude 5 Models and Server-Side Tool Support
Score
73公布了 Claude 5 系列模型具体能力和 llm-anthropic 新架构，打破常规模型发布信息差。
内容来自官方更新日志整理，结构清晰且包含关键细节，但缺乏独立评测。
为 LLM 用户提供明确的升级迁移指引，如 -T WebSearch 替代 -o 选项，可直接落地。
2026 年 8 月 4 日发布，属于即时版本更新，时效性极强。
Simon Willison 是知名开发者与 LLM 工具维护者，博客原文引用官方仓库，可信度高。
Base 81 × T2 Source weight ×0.9 = 73
Curation line 70Selected
Why selected
This release not only updates models but also changes the interaction pattern for tool calls and reasoning, carrying significant technical signal.
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.」
Quick overview
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.
- 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
Showing the source text; the full translation is being generated.
Release: llm-anthropic 0.26
Includes new features enabled by LLM 0.32:
- New models:
claude-fable-5,claude-sonnet-5, andclaude-opus-5. #75, #76- Added server-side tools for
WebSearch,WebFetch,CodeExecution, andAnthropicMCP, available through LLM's-Tinterface or Pythontools=. 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
llmCLI prompts now displays to standard error unless you pass--hide-reasoning/-R.- Simplified extended thinking to
thinkingandthinking_effort(low,medium,high,xhigh, ormax). Claude 5 models think by default;-o thinking 0disables thinking for Sonnet 5 and Opus 5, while Fable 5 always thinks.-R/--hide-reasoningnow omits reasoning from responses and logs. Thethinking_budget,thinking_display, andthinking_adaptiveoptions have been removed. #80
Tags: llm, anthropic, claude, model-context-protocol
Related items
FeaturedDeepSeek V4 Doubles Token Share on OpenRouter, Driven by Agentic Workloads
DeepSeek V4 在 OpenRouter 上的代币份额翻倍，智能体工作负载成主要驱动力
The rapid adoption of DeepSeek V4 signals a strong market preference for high-performance, low-cost inference models, especially as agentic use cases reshape AI deployment.
91
FeaturedEnabling Two Settings Triples ARC-AGI-3 Benchmark Scores
启用两项设置使ARC-AGI-3基准测试分数提升三倍
This finding is crucial! It shows that model performance depends not only on training but also on inference-time configuration. For AI engineers and researchers, this is a must-know optimization direction. Teams deploying models on resource-constrained devices in particular could find a low-cost way to boost capabilities.
91
FeaturedGPT-5.6: Fusing Frontier Intelligence with Frontier Efficiency
GPT-5.6：前沿智能与前沿效率的融合
This news is worth watching as it marks a shift from pure parameter scaling to efficiency competition. For AI developers and business decision-makers, GPT-5.6 means higher performance at lower cost, especially for long-context or agentic tasks previously hindered by inference expenses. OpenAI's move may redefine what 'frontier' means.
91
FeaturedLFM2.5-Encoders: New Models for Fast Long-Context Inference on CPU
LFM2.5-Encoder：面向CPU快速长上下文推理的新模型
This blog post catches my eye because it directly solves the pain point of running long-context LLMs on CPU. For teams or individual developers without high-end GPUs, the LFM2.5-Encoder series offers a ready-to-use open-source solution. Highly recommended for those working on RAG, document search, or code analysis—now a standard server can handle million-token documents.
91
FeaturedGPT-Red: OpenAI Automates Red Teaming via Self-Play to Boost Model Robustness
GPT-Red：OpenAI通过自我对弈实现AI红队自动化，提升模型鲁棒性
GPT-Red marks a milestone from human to automated red-teaming—essential for safety engineers and alignment researchers. While reducing cost, it also raises ethical questions about automated attacks, worth pondering for everyone in AI governance.
91
FeaturedOpenAI Launches GPT-5.5 Bio Bug Bounty Program
OpenAI推出GPT-5.5生物漏洞赏金计划
This program deserves attention as it pioneers the extension of AI bug bounty to biosecurity, offering a new research direction for the security community and a practical training ground for AI risk governance. It is particularly important for model safety researchers, biosecurity experts, and practitioners concerned about dual-use AI risks.
91
FeaturedvLLM Introduces Native-Speed Transformers Modeling Backend for Enhanced Inference Performance
vLLM推出原生速度Transformers建模后端，大幅提升推理性能
This update is critical for AI engineering teams: eliminating format conversion speeds up model iteration, and 2-5x speedup directly reduces GPU costs. If you're building LLM online services or batch inference, this is practically a must-read technical update.
90
FeaturedGoogle DeepMind Introduces SL2T, a Sign Language-to-Text Model for Deaf Users
Google DeepMind 发布手语转文本模型 SL2T，助力聋人用户
This news matters not only as a technical breakthrough but also as a sign that AI is beginning to address the needs of marginalized groups. For developers, the architecture and technical approach of SL2T merit deep study; for accessibility advocates, it's a key case for advancing industry standards.