Reasoning models

Explore advanced reasoning and problem-solving models.

Reasoning models like o3 and o4-mini are LLMs trained with reinforcement learning to perform reasoning. Reasoning models think before they answer, producing a long internal chain of thought before responding to the user. Reasoning models excel in complex problem solving, coding, scientific reasoning, and multi-step planning for agentic workflows. They're also the best models for Codex CLI, our lightweight coding agent.

As with our GPT series, we provide smaller, faster models (o4-mini and o3-mini) that are less expensive per token. The larger models (o3 and o1) are slower and more expensive but often generate better responses for complex tasks and broad domains.

To ensure safe deployment of our latest reasoning models o3 and o4-mini, some developers may need to complete organization verification before accessing these models. Get started with verification on the platform settings page.

Get started with reasoning

Reasoning models can be used through the Chat Completions endpoint as seen here.

Using a reasoning model in Chat Completions

import OpenAI from "openai";

const openai = new OpenAI();

const prompt = `
Write a bash script that takes a matrix represented as a string with 
format '[1,2],[3,4],[5,6]' and prints the transpose in the same format.
`;
 
const completion = await openai.chat.completions.create({
  model: "o4-mini",
  reasoning_effort: "medium",
  messages: [
    {
      role: "user", 
      content: prompt
    }
  ],
  store: true,
});

console.log(completion.choices[0].message.content);

from openai import OpenAI

client = OpenAI()

prompt = """
Write a bash script that takes a matrix represented as a string with 
format '[1,2],[3,4],[5,6]' and prints the transpose in the same format.
"""

response = client.chat.completions.create(
    model="o4-mini",
    reasoning_effort="medium",
    messages=[
        {
            "role": "user", 
            "content": prompt
        }
    ]
)

print(response.choices[0].message.content)

curl https://api.openai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "o4-mini",
    "reasoning_effort": "medium",
    "messages": [
      {
        "role": "user",
        "content": "Write a bash script that takes a matrix represented as a string with format \"[1,2],[3,4],[5,6]\" and prints the transpose in the same format."
      }
    ]
  }'

For the richest experience with reasoning models, we recommend using the Responses API. Because the Responses API is stateful, it can retain past reasoning items in context, delivering smarter and more token‑efficient tool usage. It also supports more features like reasoning summaries, and will soon let models invoke built-in tools when reasoning.

In the example above, the reasoning_effort parameter guides the model on how many reasoning tokens to generate before creating a response to the prompt.

Specify low, medium, or high for this parameter, where low favors speed and economical token usage, and high favors more complete reasoning. The default value is medium, which is a balance between speed and reasoning accuracy.

How reasoning works

Reasoning models introduce reasoning tokens in addition to input and output tokens. The models use these reasoning tokens to "think," breaking down the prompt and considering multiple approaches to generating a response. After generating reasoning tokens, the model produces an answer as visible completion tokens and discards the reasoning tokens from its context.

Here is an example of a multi-step conversation between a user and an assistant. Input and output tokens from each step are carried over, while reasoning tokens are discarded.

While reasoning tokens are not visible via the API, they still occupy space in the model's context window and are billed as output tokens.

Managing the context window

It's important to ensure there's enough space in the context window for reasoning tokens when creating completions. Depending on the problem's complexity, the models may generate anywhere from a few hundred to tens of thousands of reasoning tokens. The exact number of reasoning tokens used is visible in the usage object of the chat completion response object, under completion_tokens_details:

"usage": {
  "prompt_tokens": 26,
  "completion_tokens": 637,
  "total_tokens": 663,
  "prompt_tokens_details": {
    "cached_tokens": 0,
    "audio_tokens": 0
  },
  "completion_tokens_details": {
    "reasoning_tokens": 448,
    "audio_tokens": 0,
    "accepted_prediction_tokens": 0,
    "rejected_prediction_tokens": 0
  }
}

Context window lengths are found on the model reference page, and will differ across model snapshots.

Controlling costs

To manage costs with reasoning models, you can limit the total number of tokens the model generates (including both reasoning and completion tokens) by using the max_completion_tokens parameter.

In previous models, the max_tokens parameter controlled both the number of tokens generated and the number of tokens visible to the user, which were always equal. However, with reasoning models, the total tokens generated can exceed the number of visible tokens due to the internal reasoning tokens.

Because some applications might rely on max_tokens matching the number of tokens received from the API, we introduced max_completion_tokens to explicitly control the total number of tokens generated by the model, including both reasoning and visible completion tokens. This explicit opt-in ensures no existing applications break when using the new models. The max_tokens parameter continues to function as before for all previous models.

If you're managing context manually across model turns, you can discard older reasoning items unless you're responding to a function call, in which case you must include all reasoning items between the function call and the last user message.

Allocating space for reasoning

If the generated tokens reach the context window limit or the max_completion_tokens value you've set, you'll receive a chat completion response with the finish_reason set to length. This might occur before any visible completion tokens are produced, meaning you could incur costs for input and reasoning tokens without receiving a visible response.

To prevent this, ensure there's sufficient space in the context window or adjust the max_completion_tokens value to a higher number. OpenAI recommends reserving at least 25,000 tokens for reasoning and outputs when you start experimenting with these models. As you become familiar with the number of reasoning tokens your prompts require, you can adjust this buffer accordingly.

Keeping reasoning items in context

In the Chat Completions API, the model's reasoning is discarded after every API request. While this doesn't impact the model's performance in most cases, there are some complex agentic tasks involving the use of multiple function calls that see greater intelligence and high token efficiency when reasoning items are retained in context. It is only possible to retain reasoning items in context using the stateful Responses API, with the store parameter set to true.

Reasoning summaries

While we don't expose the raw reasoning tokens emitted by the model, you can view a summary of the model's reasoning via the Responses API. This feature is not supported in the Chat Completions API.

Advice on prompting

There are some differences to consider when prompting a reasoning model. Reasoning models provide better results on tasks with only high-level guidance, while GPT models often benefit from very precise instructions.

• A reasoning model is like a senior co-worker—you can give them a goal to achieve and trust them to work out the details.
• A GPT model is like a junior coworker—they'll perform best with explicit instructions to create a specific output.

For more information on best practices when using reasoning models, refer to this guide.

Prompt examples

Coding (refactoring)

OpenAI o-series models are able to implement complex algorithms and produce code. This prompt asks o1 to refactor a React component based on some specific criteria.

Refactor code

import OpenAI from "openai";

const openai = new OpenAI();

const prompt = `
Instructions:
- Given the React component below, change it so that nonfiction books have red
  text. 
- Return only the code in your reply
- Do not include any additional formatting, such as markdown code blocks
- For formatting, use four space tabs, and do not allow any lines of code to 
  exceed 80 columns

const books = [
  { title: 'Dune', category: 'fiction', id: 1 },
  { title: 'Frankenstein', category: 'fiction', id: 2 },
  { title: 'Moneyball', category: 'nonfiction', id: 3 },
];

export default function BookList() {
  const listItems = books.map(book =>
    <li>
      {book.title}
    </li>
  );

  return (
    <ul>{listItems}</ul>
  );
}
`.trim();

const completion = await openai.chat.completions.create({
  model: "o4-mini",
  messages: [
    {
      role: "user",
      content: prompt,
    },
  ],
  store: true,
});

console.log(completion.choices[0].message.content);

from openai import OpenAI

client = OpenAI()

prompt = """
Instructions:
- Given the React component below, change it so that nonfiction books have red
  text. 
- Return only the code in your reply
- Do not include any additional formatting, such as markdown code blocks
- For formatting, use four space tabs, and do not allow any lines of code to 
  exceed 80 columns

const books = [
  { title: 'Dune', category: 'fiction', id: 1 },
  { title: 'Frankenstein', category: 'fiction', id: 2 },
  { title: 'Moneyball', category: 'nonfiction', id: 3 },
];

export default function BookList() {
  const listItems = books.map(book =>
    <li>
      {book.title}
    </li>
  );

  return (
    <ul>{listItems}</ul>
  );
}
"""

response = client.chat.completions.create(
    model="o4-mini",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": prompt
                },
            ],
        }
    ]
)

print(response.choices[0].message.content)

Coding (planning)

OpenAI o-series models are also adept in creating multi-step plans. This example prompt asks o1 to create a filesystem structure for a full solution, along with Python code that implements the desired use case.

Plan and create a Python project

import OpenAI from "openai";

const openai = new OpenAI();

const prompt = `
I want to build a Python app that takes user questions and looks 
them up in a database where they are mapped to answers. If there 
is close match, it retrieves the matched answer. If there isn't, 
it asks the user to provide an answer and stores the 
question/answer pair in the database. Make a plan for the directory 
structure you'll need, then return each file in full. Only supply 
your reasoning at the beginning and end, not throughout the code.
`.trim();

const completion = await openai.chat.completions.create({
  model: "o4-mini",
  messages: [
    {
      role: "user",
      content: prompt,
    },
  ],
  store: true,
});

console.log(completion.choices[0].message.content);

from openai import OpenAI

client = OpenAI()

prompt = """
I want to build a Python app that takes user questions and looks 
them up in a database where they are mapped to answers. If there 
is close match, it retrieves the matched answer. If there isn't, 
it asks the user to provide an answer and stores the 
question/answer pair in the database. Make a plan for the directory 
structure you'll need, then return each file in full. Only supply 
your reasoning at the beginning and end, not throughout the code.
"""

response = client.chat.completions.create(
    model="o4-mini",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": prompt
                },
            ],
        }
    ]
)

print(response.choices[0].message.content)

STEM Research

OpenAI o-series models have shown excellent performance in STEM research. Prompts asking for support of basic research tasks should show strong results.

Ask questions related to basic scientific research

import OpenAI from "openai";

const openai = new OpenAI();

const prompt = `
What are three compounds we should consider investigating to 
advance research into new antibiotics? Why should we consider 
them?
`;
 
const completion = await openai.chat.completions.create({
  model: "o4-mini",
  messages: [
    {
      role: "user", 
      content: prompt,
    }
  ],
  store: true,
});

console.log(completion.choices[0].message.content);

from openai import OpenAI

client = OpenAI()

prompt = """
What are three compounds we should consider investigating to 
advance research into new antibiotics? Why should we consider 
them?
"""

response = client.chat.completions.create(
    model="o4-mini",
    messages=[
        {
            "role": "user", 
            "content": prompt
        }
    ]
)

print(response.choices[0].message.content)

Use case examples

Some examples of using reasoning models for real-world use cases can be found in the cookbook.

Using reasoning for data validation

Evaluate a synthetic medical data set for discrepancies.

Using reasoning for routine generation

Use help center articles to generate actions that an agent could perform.