Source URL: https://simonwillison.net/2025/May/22/llm-anthropic-016/#atom-everything
Source: Simon Willison’s Weblog
Title: llm-anthropic 0.16
Feedly Summary: llm-anthropic 0.16
New release of my LLM plugin for Anthropic adding the new Claude 4 Opus and Sonnet models.
You can see pelicans on bicycles generated using the new plugin at the bottom of my live blog covering the release.
I also released llm-anthropic 0.16a1 which works with the latest LLM alpha and provides tool usage feature on top of the Claude models.
The new models can be accessed using both their official model ID and the aliases I’ve set for them in the plugin:
llm install -U llm-anthropic
llm keys set anthropic
# paste key here
llm -m anthropic/claude-sonnet-4-0 \
‘Generate an SVG of a pelican riding a bicycle’
This uses the full model ID – anthropic/claude-sonnet-4-0.
I’ve also setup aliases claude-4-sonnet and claude-4-opus. These are notably different from the official Anthropic names – I’m sticking with their previous naming scheme of claude-VERSION-VARIANT as seen with claude-3.7-sonnet.
Here’s an example that uses the new alpha tool feature with the new Opus:
llm install llm-anthropic==0.16a1
llm –functions ‘
def multiply(a: int, b: int):
return a * b
‘ ‘234324 * 2343243’ –td -m claude-4-opus
Outputs:
I’ll multiply those two numbers for you.
Tool call: multiply({‘a’: 234324, ‘b’: 2343243})
549078072732
The result of 234,324 × 2,343,243 is **549,078,072,732**.
Here’s the output of llm logs -c from that tool-enabled prompt response. More on tool calling in my recent workshop.
Tags: llm, anthropic, claude, generative-ai, ai, llms
AI Summary and Description: Yes
Summary: The text discusses the release of a new version of a plugin for Anthropic’s language models, specifically the Claude 4 Opus and Sonnet models. It highlights enhancements including a tool usage feature and showcases examples of how to use the models effectively through specific commands. This is particularly relevant for professionals in AI and LLM security impressed by the continual evolution of generative AI technologies.
Detailed Description: The text provides detailed information about the release of the plugin version llm-anthropic 0.16 and its subsequent alpha version 0.16a1. The following points summarize the significance of this update:
– **Plugin Release**: Introduction of the llm-anthropic plugin version 0.16, which interfaces with the new Claude 4 Opus and Sonnet models.
– **New Features**:
– Enhanced tool usage capabilities added to the plugin with the alpha version, enabling users to execute functions directly through prompts.
– The ability to generate specific outputs (e.g., graphics or mathematical results) by calling predefined functions within the language model.
– **Installation Commands**:
– The text includes detailed commands on how users can install the plugin and set it up to access the new models, demonstrating practical steps for technical implementation.
– **Alias Setup**:
– Users can access the models using both the official IDs and custom aliases, which shows flexibility and eases navigation within the tool.
– **Example Usage**: A clear example is provided, showing how to multiply two numbers using a defined function, complete with sample output, showcasing the practical utility of the new features.
– **Community Engagement**: The author mentions sharing this information through a live blog and a recent workshop, indicating an effort to educate and engage fellow professionals about the implementation of these new features and the capabilities of generative AI models.
Overall, this text is highly relevant to the fields of AI and LLM security, illustrating ongoing advancements in AI technologies and their potential applications, which security professionals may need to consider for integration, compliance, and risk management in AI systems.