ReqAI

ReqAI is a lightweight Elixir client for LLM APIs, built on Req.

{:ok, %Req.Response{}, %{"output" => [%{"content" => [content]}]}} =
  ReqAI.generate(ReqAI.Provider.OpenAI, 
    model: "gpt-5.4-mini",
    input: "Say hello"
  )

IO.puts(content["text"])

See the Getting Started guide for configuration and usage examples.

Features

• Generate and stream with one calling convention, using each provider's request and response formats.
• Built-in adapters for Anthropic, OpenAI, Gemini, xAI, and OpenRouter. Add custom adapters with the Provider behaviour.
• Telemetry for request lifecycle, duration, token usage, and time to first chunk. Customize metadata with the Telemetry behaviour.
• Configure authentication, retries, timeouts, and testing through Req.
• Optional translators for your own request, response, error, and event shapes.

Installation

Add ReqAI to your dependencies in mix.exs:

{:req_ai, ">= 0.0.0"}

Requires Elixir 1.18 or later and Req 0.8.0 or later.