研究一下，OpenAI最新推出的o3-deep-research（06-25），是否就是官网当中使用...

Crafting answer on o3-deep-research

I need to clarify a few things about o3-deep-research. It's a fine-tuned version of the o3 model, enhanced for agentic deep research tasks and tool interaction.

On the ChatGPT site, the base model is simply "OpenAI o3," but the deep research version shares the same core while adding specific tuning for tasks like browsing and Python processing.

For developers, there's also a model ID called "o3-deep-research" available since June 25.

This means that deep research might perform differently from o3, and it can be slower, with browsing integrated.

Crafting the response about o3-deep-research

o3-deep-research is a fine-tuned variant of o3, designed for deeper research tasks with integrated tool use. It's based on the same core weights but includes specialized tuning for browsing, Python, and data retrieval, perhaps offering longer context windows.

On the ChatGPT site, the "o3" references the base model, while "o3-deep-research" has been available for developers since June 25, 2025, offering autonomous search and citation capabilities. This version tends to perform slower than the base model due to its advanced features.

Thought for 53 seconds

Gathering deep research info

I need to find the latest details on deep research pricing and features, so I'll search for "o3-deep-research price API." Deep research relies on a combination of search and Python tools, which I’ll need to gather more about. I'll check the FAQ for relevant info, such as usage limits, and also review context window details (200k tokens). Finally, I'll pull at least 10 high-quality citations from diverse sources, such as openai.com, help.openai.com, and trusted news sites.

Organizing and gathering citations

I need to organize the ways I'll get citations. Here's my plan: I’ll gather sources like OpenAI’s community pages and pricing details, help pages on FAQs, and news sites like Axios, The Guardian, and Reuters. I'll also look for insights from blogs like MarketingAIInstitute and alexop.dev. With at least 15 diverse citations, I'll compile a summary that includes deployment channel, primary use case, pricing, and more. This summary will be clear and structured, using markdown with tables to clarify differences in API features like context window, output style, and query limits.

Thought for 57 seconds

Clarifying differences between o3 API and ChatGPT o3

The main difference between the o3 API and ChatGPT o3 is not about capabilities but about the interface and tool availability. Both can handle multi-step reasoning, and the API can also use tools, if configured. The key distinction is that ChatGPT UI provides built-in orchestration for multi-turn thinking and automatic tool usage (like browsing or code), whereas the o3 API requires extra setup for these tools. The default environment influences user convenience more than the underlying abilities.

Summarizing response on o3-deep-research API and tools

To clarify, the o3-deep-research API does support multi-step reasoning and can use tools, particularly for in-depth research tasks. It autonomously searches and reads, which is a specialized feature for deep research. The tools (like browsing and Python) are hosted by OpenAI, so the user does not need to implement them, though they can add custom tools as needed. Numerous citations reinforce these features, including official OpenAI documentation, tutorials, and community posts.

Thought for 45 seconds