LLM

What is LLM?

LLM is a command-line tool and Python library for talking to large language models from a terminal or a script. It reaches remote models from OpenAI, Anthropic's Claude, Google's Gemini, Mistral, DeepSeek and others through an API key, and it runs models on your own machine through plugins, for example with Ollama. From the shell you can run a one-off prompt, pipe a file in with a system prompt, attach an image or PDF, or open an interactive chat. Every prompt and response can be stored in a SQLite database, embeddings can be generated and stored, structured content can be extracted with schemas, and models can be given tools to run. Templates, fragments and model aliases keep repeated work tidy, and a plugin directory adds more models. LLM is open source and installs with pip, Homebrew, pipx or uv. There are no plans or subscription fees, though the hosted providers charge for their own APIs.

Use cases

• Run prompts from the command line
• Pipe files into a model with a system prompt
• Log prompts and responses to SQLite
• Generate and store embeddings
• Extract structured data from images and text
• Give models tools to call
• Chat with local models through Ollama

Who it's for

• Developers
• Command-line users
• Python programmers
• Data analysts

Why use LLM

• One interface covers many providers, so switching models means changing a flag rather than rewriting a script.
• Logging to SQLite gives you a searchable record of what you asked and what came back.
• It works in shell pipelines, so file contents or command output can be fed straight to a model.
• Plugins add local and hosted models without changing how you use the tool.
• Free and open source, with no subscription of its own.

LLM features

• Command-line interface and Python API for many models
• Plugins for Gemini, Anthropic and local models such as Ollama
• Interactive chat mode with multi-line and editor input
• SQLite logging of prompts and responses
• Embeddings generation and storage
• Schemas for extracting structured content
• Tool support so models can run functions
• Templates, fragments and model aliases
• Image and PDF attachments for models that accept them
• Chat against any OpenAI-compatible endpoint, such as LM Studio

LLM integrations

• OpenAI
• Anthropic
• Google Gemini
• Ollama
• LM Studio
• SQLite
• Mistral
• DeepSeek

How to get started with LLM

1. Install LLM with pip, Homebrew, pipx or uv.
2. Store an API key with the llm keys set command, or install a plugin such as llm-gemini, llm-anthropic or llm-ollama.
3. Run a prompt from the terminal, optionally with a system prompt, an attachment or piped input.
4. Start llm chat for a back-and-forth session with a chosen model.
5. Review logged conversations in SQLite and save templates, schemas or aliases for work you repeat.

LLM limitations

• Hosted models need your own API key and are billed by the provider
• It is a command-line tool with no graphical interface
• Non-OpenAI providers and local models need plugins installed first

LLM pricing

LLM is open source, so you can use and self-host it for free.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

LLM alternatives

The main LLM alternatives listed on Debuly are Ollama, Fabric, LiteLLM, BAML, Z.AI Developer Platform and Alibaba Cloud Model Studio. The table compares pricing and platforms; order is A–Z.

1. 

   Alibaba Cloud Model Studio

   Alibaba Cloud platform giving developers API access to Qwen and partner models for text, image, video and speech, billed per token or by subscription.

   Developer platformsAudio and voiceVideo
   PaidVisit Alibaba Cloud Model Studio (official site)
2. 

   BAML

   Open-source, TypeScript-like programming language for agents, with typed LLM functions, built-in tests and SDK generation.

   Developer platformsCoding
   Open sourceVisit BAML (official site)
3. 

   Fabric

   Open-source framework by Daniel Miessler that stores AI prompts as reusable patterns you run from the command line.

   Developer platformsProductivityChat assistants
   Open sourceVisit Fabric (official site)
4. 

   LiteLLM

   Open-source AI gateway and Python SDK that gives one OpenAI-format API to 100+ LLM providers, with keys, budgets and cost tracking.

   Developer platformsCodingAutomation and agents
   Open sourceVisit LiteLLM (official site)
5. 

   Ollama

   Open-source app and CLI for running open AI models locally on macOS, Windows and Linux, with optional paid cloud models.

   Developer platformsCodingChat assistants
   Open sourceVisit Ollama (official site)
6. 

   Z.AI Developer Platform

   Pay-per-token API for Z.AI's GLM models, plus a monthly GLM Coding Plan that powers coding agents such as Claude Code.

   Developer platformsCoding
   FreemiumVisit Z.AI Developer Platform (official site)

LLM FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from llm.datasette.io · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.