# GPT reasoning settings: reasoning_effort, reasoning summaries and verbosity

Source: https://ofox.ai/docs/develop/models/gpt/reasoning

This page covers reasoning effort, reasoning summaries and answer length control for the GPT family. For model IDs and endpoint setup, see the [GPT family overview](https://ofox.ai/docs/develop/models/gpt).

**Key point**:Reasoning tokens count toward the output limit. Leave enough max_completion_tokens when reasoning is enabled, or the answer may be empty.

GPT-5 and later models support reasoning: they reason internally before answering, which helps with math, code and multi-step analysis.

| Item | Chat Completions | Responses |
|---|---|---|
| Reasoning effort | `"reasoning_effort": "high"` | `"reasoning": {"effort": "high"}` |
| Reasoning token count | `usage.completion_tokens_details.reasoning_tokens` | `usage.output_tokens_details.reasoning_tokens` |
| Reasoning content | Not returned | Reasoning summary — see below |

- Common values are `low`, `medium` and `high`. Higher effort means more reasoning tokens and longer latency. Passing a value the model doesn't support returns 400, and the error message lists the values that model supports.
- When `reasoning_effort` is omitted, the default differs by model: for example, GPT-5.4 and GPT-6 Sol do not reason by default, while GPT-5 does. Pass it explicitly when you need reasoning.
- Reasoning tokens are billed at the output rate and count toward `max_completion_tokens` (`max_output_tokens` in Responses).

## Reasoning summaries
The Responses API can return a summary of the reasoning process; Chat Completions does not return reasoning content:

```python filename="gpt_reasoning_summary.py"
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.ofox.ai/v1", api_key=os.environ["OFOX_API_KEY"])

resp = client.responses.create(
    model="openai/gpt-5.4",
    reasoning={"effort": "medium", "summary": "auto"},
    max_output_tokens=20000,
    input="Find all positive integers n less than 50 for which n² + n + 41 is not prime, and briefly explain why.",
)
for item in resp.output:
    if item.type == "reasoning":
        for s in item.summary:
            print("[Reasoning summary]", s.text)
print("[Answer]", resp.output_text)
```

`output` may contain several `reasoning` items, and some have an empty `summary` array, so check each one as you read them. When there is little reasoning, there may be no summary.

## Controlling answer length
GPT-5 series models support `verbosity` in Chat Completions, with values `low`, `medium` and `high`, to control how detailed the answer is. Unlike `max_completion_tokens`, it does not truncate the answer.

For other errors, see [Common errors](https://ofox.ai/docs/develop/models/gpt#errors).