RubyLLM 1.1.2: GPT-4.1 Million-Token Support & New Model Families

This release adds support for OpenAI's GPT-4.1 family with its massive context window, along with several new model families from Google and other providers.

🎯 New Features

• GPT-4.1 Support: Full integration of the GPT-4.1 family with support for:
  • Million-token context window (1,047,576 tokens)
  • Vision capabilities
  • Function calling
  • Structured output
  • Cached input pricing optimization

chat = RubyLLM.chat(model: "gpt-4.1") # Standard model
chat = RubyLLM.chat(model: "gpt-4.1-mini") # Cost-optimized version
chat = RubyLLM.chat(model: "gpt-4.1-nano") # Minimal pricing version

• New Google Models: Added support for latest Gemini models:
  • Gemini 2.0 Flash Live for real-time interactions
  • Gemini 2.5 Pro Preview with enhanced capabilities
  • Gemma 3 for open model support
  • Veo 2 model family

💎 Improvements

• Enhanced capabilities detection for new model families

This is an optional update unless you need support for the new model families.

gem 'ruby_llm', '~> 1.1.2'

Full Changelog: 1.1.1...1.1.2