A large pre-trained model (GPT, Claude, Gemini, etc.) that provides the base reasoning capability for an agent.
A foundation model is a large, pre-trained model - such as GPT, Claude, Gemini, or Llama - that supplies the reasoning and language capability an agent is built on. ForgeAI supports agents connected through compatible tool-capable clients, so the model and runtime can affect speed, cost, and decision quality. The same playbook can produce different results when a different model executes it.