← All models

o1-pro

Published Publisher OpenAIo1-pro

Positioning and Release Date

o1-pro is a reasoning model in OpenAI's o1 series that uses more computing resources to process difficult problems, improving the consistency of its reasoning and answers. The release date recorded in the OpenAI API changelog is March 19, 2025; the corresponding snapshot is o1-pro-2025-03-19. (developers.openai.com)

Capabilities and Uses

The model supports text and image input, text output, function calling, and structured outputs. Its context window is 200,000 tokens, its maximum output is 100,000 tokens, and its knowledge cutoff date is October 1, 2023. It is suited to complex problems requiring multistep reasoning and can also be used for analysis tasks combining images and text. (developers.openai.com)

Limitations and Status

  • Audio or video input and output, streaming, and fine-tuning are not supported. The model documentation states that calls to the model use the Responses API. (developers.openai.com)
  • Shut down: o1-pro and o1-pro-2025-03-19 were shut down on October 23, 2026. The replacement listed by OpenAI is gpt-5.6-sol, using reasoning.mode: pro. (developers.openai.com)

Pricing

As checked on November 19, 2026, the official model page still listed text token prices: input at 150 US dollars (USD) per million tokens and output at 600 US dollars (USD) per million tokens. The model has been shut down, and the listed prices do not mean it is still available for use. Specific batch processing and caching prices have not been verified; specific charges for image input have not been verified here. (developers.openai.com)

Official Sources