͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
We’re excited to introduce GPT‑5.5, our smartest and most intuitive to use model yet, and the next step toward a new way of getting work done on a computer. GPT-5.5 is now available in the API, Codex, and ChatGPT.
GPT‑5.5 understands what you’re trying to do faster and can carry more of the work itself. It also uses significantly fewer tokens to complete the same tasks, making it more efficient as well as more capable.
To get the most out of GPT-5.5 in the API, check out our API prompt guide and migration guide, or use the command: [$openai-docs migrate this project to gpt-5.5] to kick off a plan to migrate your API integration via Codex.
GPT-5.5 is now the default model in Codex.
|
|
|
Here’s how GPT-5.5 powers key capabilities:
Agentic coding: GPT‑5.5 is our strongest agentic coding model to date. The model’s coding strengths show up especially clearly in Codex where it can take on engineering work ranging from implementation and refactors to debugging, testing, and validation.
Knowledge work: The same strengths that make GPT‑5.5 great at coding also make it powerful for everyday work on a computer. When combined with Codex’s computer use skills, GPT‑5.5 brings us closer to the feeling that the model can actually use the computer with you: seeing what’s on screen, clicking, typing, navigating interfaces, and moving across tools with precision.
Scientific and technical research: GPT‑5.5 also shows gains on scientific and technical research workflows, which require more than answering a hard question. Researchers need to explore an idea, gather evidence, test assumptions, interpret results, and decide what to try next. GPT‑5.5 is better at persisting across that loop than other models.
|
|
|
