This model always redirects to the latest model in the OpenAI GPT family.
This model always redirects to the latest model in the OpenAI GPT family.
OpenAI GPT Latest costs $2.50/M input tokens and $15.00/M output tokens, with separate rates for Cache Read at $0.25/M tokens, Cache Write at $3.125/M tokens and Web Search at $10.00/1K calls.
OpenAI GPT Latest has a 1,050,000 token context window. It supports up to 128,000 completion tokens.
Yes. OpenAI GPT Latest accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
OpenAI GPT Latest accepts files such as PDFs, images and text as input and returns text.
GPT-5.6 Luna Pro, GPT-5.6 Luna, GPT-5.6 Terra Pro and 55 more are other text models from OpenAI.
OpenAI GPT Latest was released on April 27, 2026. Its knowledge cutoff is February 16, 2026.
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.