Elixir

Universal LLM API client for Elixir. Access 143+ LLM providers through a single interface with native BEAM concurrency, OTP integration, and idiomatic Elixir API.

Installation

Package Installation

Add to your mix.exs dependencies:

def deps do
  [
    {:liter_llm, "~> 1.2.0"}
  ]
end

Then run:

mix deps.get

System Requirements

• Elixir 1.14+ and Erlang/OTP 25+ required
• API keys via environment variables (e.g. OPENAI_API_KEY, ANTHROPIC_API_KEY)

Quick Start

Basic Chat

Send a message to any provider using the provider/model prefix:

{:ok, response} =
  LiterLlm.chat(
    %{
      model: "openai/gpt-4o",
      messages: [%{role: "user", content: "Hello!"}]
    },
    api_key: System.fetch_env!("OPENAI_API_KEY")
  )

IO.puts(hd(response["choices"])["message"]["content"])

Common Use Cases

Streaming Responses

Stream tokens in real time:

{:ok, chunks} =
  LiterLlm.Client.chat_stream(client, %{
    model: "openai/gpt-4o-mini",
    messages: [%{role: "user", content: "Hello"}]
  })

for chunk <- chunks, do: IO.inspect(chunk)

Next Steps

• Provider Registry - Full list of supported providers
• GitHub Repository - Source, issues, and discussions

Features

Supported Providers (143+)

Route to any provider using the provider/model prefix convention:

Complete Provider List

Key Capabilities

• Provider Routing -- Single client for 143+ LLM providers via provider/model prefix

• Local LLMs — Connect to locally-hosted models via Ollama, LM Studio, vLLM, llama.cpp, and other local inference servers

• Unified API -- Consistent chat, chat_stream, embeddings, list_models interface

• Streaming -- Real-time token streaming via chat_stream

• Tool Calling -- Function calling and tool use across all supporting providers

• Type Safe -- Schema-driven types compiled from JSON schemas

• Secure -- API keys never logged or serialized, managed via environment variables

• Observability -- Built-in OpenTelemetry with GenAI semantic conventions

• Error Handling -- Structured errors with provider context and retry hints

Performance

Built on a compiled Rust core for speed and safety:

• Provider resolution at client construction -- zero per-request overhead
• Configurable timeouts and connection pooling
• Zero-copy streaming with SSE and AWS EventStream support
• API keys wrapped in secure memory, zeroed on drop

Provider Routing

Route to 143+ providers using the provider/model prefix convention:

openai/gpt-4o
anthropic/claude-3-5-sonnet-20241022
groq/llama-3.1-70b-versatile
mistral/mistral-large-latest

See the provider registry for the full list.

Proxy Server

liter-llm also ships as an OpenAI-compatible proxy server with Docker support:

docker run -p 4000:4000 -e LITER_LLM_MASTER_KEY=sk-your-key ghcr.io/kreuzberg-dev/liter-llm

See the proxy server documentation for configuration, CLI usage, and MCP integration.

Documentation

• Documentation -- Full docs and API reference
• GitHub Repository -- Source, issues, and discussions
• Provider Registry -- 143 supported providers

Part of kreuzberg.dev.

Contributing

Contributions are welcome! See CONTRIBUTING.md for guidelines.

Join our Discord community for questions and discussion.

License

MIT -- see LICENSE for details.