GPT-5.1

GPT-5.1 arrived on 13 November 2025, three months after GPT-5, as OpenAI's flagship for coding and agentic work. The hard numbers did not move: a 400,000-token context window, 128,000 tokens of output, text and image input, text output, and the same $1.25 per million input tokens and $10 per million output that GPT-5 had launched with. The knowledge cutoff also stayed at 30 September 2024. What changed was control. GPT-5.1 was the first model in the family where reasoning effort could be set to "none" as the default, alongside low, medium and high — a single parameter that turns a reasoning model into a fast conversational one without switching endpoints. The pattern stuck: every later GPT-5 generation ships with the same dial, and GPT-5.2 extended it upwards with an "xhigh" setting. The generation was broad but short-lived at the edges. OpenAI released gpt-5.1-codex and gpt-5.1-codex-mini the day after launch and gpt-5.1-codex-max two weeks later; all three, together with gpt-5.1-chat-latest, were shut down on 23 July 2026 and pointed at GPT-5.6. The base gpt-5.1 model has no announced shutdown date and remains available in the API.

▸Videos

No videos yet.

▸Reviews