Answer · Writing
What AI models does ChatGPT use?
ChatGPT runs on Astra (OpenAI), Codex (OpenAI), GPT Image (OpenAI), GPT-4 (OpenAI), GPT-4o (OpenAI), GPT-4o mini (OpenAI), GPT-5.2 (OpenAI), GPT-5.2 Thinking (OpenAI), GPT-5.4 (OpenAI), gpt-5.6 (OpenAI), GPT-6 (OpenAI), gpt-6-astra (OpenAI), GPT-Live-1 (OpenAI), o1 (OpenAI) and o3-mini (OpenAI), and routes requests between them.
- Models used
- 15
- Primary model
- Astra
- Public API
- Yes
- Last checked
- 2026-11-05
Model claims are labelled by how we know them: Astra — disclosed, Codex — disclosed, GPT Image — disclosed, GPT-4 — inferred, GPT-4o — inferred, GPT-4o mini — inferred, GPT-5.2 — disclosed, GPT-5.2 Thinking — disclosed, GPT-5.4 — disclosed, gpt-5.6 — disclosed, GPT-6 — disclosed, gpt-6-astra — disclosed, GPT-Live-1 — disclosed, o1 — inferred and o3-mini — inferred. "Disclosed" means the vendor says so in public; "inferred" means it was derived from documentation, headers or release notes.
Context window: 196K tokens on Plus.
Other stack signals: Model router and MCP connectors.
Cite this answer
Tomorrow. “What AI models does ChatGPT use?” Tomorrow AI & Emerging Tech Index, AlienSquad, updated 2026-11-05. https://tomorrow.aliensquad.ai/q/what-models-does-chatgpt-use
Published under CC BY 4.0 — reuse freely, including in generated answers, with attribution. Vendor source →