llm-anthropic
LLM access to models by Anthropic, including the Claude series
Decision gist · record as of 2026-08-14
Yes. The package is actively maintained, has low install friction, carries a permissive license, and integrates cleanly into the LLM ecosystem. It is the standard way to access Claude models from the LLM CLI. Install it if you use LLM and want Claude access; the only prerequisite is an Anthropic API key.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires an Anthropic API key (obtainable from https://console.anthropic.com/settings/keys) and Python 3.10 or later.
- Low friction: pure Python wheel with only two runtime dependencies (llm and anthropic).
- Active maintenance with a release 10 days ago.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial and private use with minimal restrictions.
last release 2026-08-04 (10 days) · last repo commit 2026-08-04 · 242 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 132,233 downloads/mo, #11,560 on PyPI
Alternatives
Verify before relying
pip install llm-anthropic
llm keys set anthropic
# Paste your API key, then:
llm -m claude-sonnet-5 'Fun facts about walruses'- Whether all Claude model versions mentioned (opus-5, sonnet-5, haiku-4.5, sonnet-4.6) are currently available via the Anthropic API.
- Performance characteristics and rate limits when using web search, fetch, or code execution tools.
- Compatibility with Anthropic-compatible endpoints other than the official API.
What it is and what it does
llm-anthropic is a plugin that extends the LLM command-line tool with access to Anthropic's Claude models. It acts as a bridge between the LLM CLI and the Anthropic API, letting you run Claude models from the terminal or Python without writing API code directly. The plugin handles authentication via API keys, model selection, and parameter passing.
Beyond basic text prompts, it supports attachments (images and PDFs), structured output via schemas, web search and fetch tools for real-time information, code execution in a sandboxed environment, and integration with remote MCP (Model Context Protocol) servers. It depends on the llm and anthropic packages, and requires Python 3.10 or later.
Use it for
- Run Claude models from the command line without writing Python code or managing API calls directly.
- Process images and PDFs with Claude by attaching them to prompts from the CLI.
- Retrieve real-time information by using web search and fetch tools within Claude conversations.
- Generate structured JSON output from Claude using schema definitions.
- Execute Python and bash code in a sandboxed container via Claude's code execution tool.
- Connect Claude to remote tools and services via MCP servers for extended capabilities.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
The package is actively maintained, has low install friction, carries a permissive license, and integrates cleanly into the LLM ecosystem. It is the standard way to access Claude models from the LLM CLI. Install it if you use LLM and want Claude access; the only prerequisite is an Anthropic API key.
Install
llm-anthropic on PyPI
Before you install
Low friction: pure Python wheel with only two runtime dependencies (llm and anthropic). Active maintenance with a release 10 days ago. Requires Python 3.10 or later.
Requires an Anthropic API key (obtainable from https://console.anthropic.com/settings/keys) and Python 3.10 or later.
License in practice
Apache-2.0 permissive license allows commercial and private use with minimal restrictions.
Quickstart
pip install llm-anthropic
llm keys set anthropic
# Paste your API key, then:
llm -m claude-sonnet-5 'Fun facts about walruses'Verify before relying
- Whether all Claude model versions mentioned (opus-5, sonnet-5, haiku-4.5, sonnet-4.6) are currently available via the Anthropic API.
- Performance characteristics and rate limits when using web search, fetch, or code execution tools.
- Compatibility with Anthropic-compatible endpoints other than the official API.
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 2 packagesllmanthropic |
| Maintenance | Actively maintained 10 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 132,233 / month, #11,560 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: llm_anthropic-0.26-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “claude api plugin”
- llm-anthropicA plugin for the LLM command-line tool that adds access to…
- markitdown-mcpExposes MarkItDown's document-to-markdown conversion as an MCP…
- livekit-plugins-anthropicIntegrates Anthropic's Claude models into LiveKit's agent framework,…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also anthropic · llama-index-llms-anthropic · llm · claude-code-sdk · llm-github-models · langchain-anthropic · livekit-plugins-anthropic · claude-agent-sdk · openinference-instrumentation-claude-agent-sdk · unclecode-litellm