GPT (model family)
Published Updated
What is GPT (model family)?
The foundational series of large language models created by OpenAI, driving ChatGPT and widely integrated into developer tools and enterprise APIs.
The Generative Pre-trained Transformer (GPT) family comprises robust, general-purpose models. The current Orbit ladder names its small, middle, and frontier GPT tiers Luna, Sol, and Astra. They combine reasoning, multimodal understanding (audio/vision), and autonomous tool execution for applications and developer copilots.
How it relates to Orbit
Orbit can route work to Codex and to custom OpenAI-compatible model endpoints. See Complexity Tiers & Routing for details.
When you would use it
You use a GPT model when you require a highly generalized, industry-standard AI backend that excels across text generation, reasoning, and multimodal inputs.
Common operations
- Powering conversational AI interfaces and copilots.
- Executing complex, generalized reasoning and coding tasks.