Source: Models (OpenAI API docs)

OpenAI's model catalogue: the GPT-6 family (Astra, Sol, Terra, Luna) with context windows, output limits, prices, cutoffs and reasoning-effort levels.

Contents
  • What: official API documentation page
  • Publisher: OpenAI
  • Date: accessed 2026-11-14
  • Original: Models

Summary

Lists OpenAI’s current flagship text models and how to pick among them. Each model exposes a reasoning-effort setting rather than a separate reasoning model line.

Key claims

  • Current family (2026-11-14): GPT-6 Astra (most capable, $10/$50), GPT-6.1 Sol (near-Astra at $2/$10), GPT-6.1 Terra (visual reasoning, computer use, writing; $1/$5), GPT-6 Luna (most efficient, $0.10/$0.50).
  • All four list a 1.05M-token context window and 128K max output.
  • Knowledge cutoffs: Astra and Sol 2026-04-30, Luna 2026-05-18, Terra 2026-06-01.
  • Reasoning effort: Astra and Sol accept low to max; Terra and Luna also accept none.
  • Recommendations: Astra for complex reasoning and coding, Sol for capability/cost balance, Luna for cost-sensitive high-volume work.
  • The catalogue page does not list the gpt-oss open-weight models.

Feeds

Frontier model landscape · Model selection

Suggest changes →