Reasoning Models | NeuraAI Documentation

NeuraAI’s reasoning models are designed to tackle complex problems by thinking through solutions step-by-step before responding. These models excel at mathematical reasoning, advanced coding challenges, scientific analysis, and multi-stage planning.

How Reasoning Works

Unlike standard language models that generate responses immediately, reasoning models create an internal chain of thought, exploring different approaches and evaluating solutions before providing their final answer.

Available Models

o4-mini - Fast reasoning for everyday complex tasks
gemini-2.5-pro - Advanced reasoning for challenging problems

Basic Example

1 from openai import OpenAI
2 
3 client = OpenAI(
4     base_url="https://api.neura-ai.app/v1"
5 )
6 
7 prompt = """
8 Write a bash script that accepts a matrix in the format 
9 '[1,2],[3,4],[5,6]' and outputs its transpose in the same format.
10 """
11 
12 response = client.chat.completions.create(
13     model="o4-mini",
14     reasoning_effort="medium",
15     messages=[
16         {
17             "role": "user",
18             "content": prompt
19         }
20     ]
21 )
22 
23 print(response.choices[0].message.content)

Reasoning Effort Levels

Control how deeply the model thinks with the reasoning_effort parameter:

Low Effort

Faster responses
Lower token usage
Suitable for moderately complex problems

1 response = client.chat.completions.create(
2     model="o4-mini",
3     reasoning_effort="low",
4     messages=[{"role": "user", "content": "Solve this algebra problem: 2x + 5 = 13"}]
5 )

Medium Effort (Default)

Balanced performance
Good for most use cases
Recommended starting point

1 response = client.chat.completions.create(
2     model="o4-mini",
3     reasoning_effort="medium",
4     messages=[{"role": "user", "content": "Design an algorithm to find the shortest path in a weighted graph"}]
5 )

High Effort

Most thorough reasoning
Higher token consumption
Best for very complex problems

1 response = client.chat.completions.create(
2     model="o4-mini",
3     reasoning_effort="high",
4     messages=[{"role": "user", "content": "Prove the Pythagorean theorem using multiple different approaches"}]
5 )

Ideal Use Cases

Mathematical Problem Solving

1 response = client.chat.completions.create(
2     model="gemini-2.5-pro",
3     reasoning_effort="high",
4     messages=[{
5         "role": "user",
6         "content": "Solve this optimization problem: Minimize f(x,y) = x² + y² subject to x + 2y = 4"
7     }]
8 )

Complex Coding Challenges

1 response = client.chat.completions.create(
2     model="o4-mini",
3     reasoning_effort="medium",
4     messages=[{
5         "role": "user",
6         "content": "Implement a balanced binary search tree with insert, delete, and search operations in Python"
7     }]
8 )

Scientific Reasoning

1 response = client.chat.completions.create(
2     model="gemini-2.5-pro",
3     reasoning_effort="high",
4     messages=[{
5         "role": "user",
6         "content": "Explain the thermodynamic principles behind refrigeration and calculate the efficiency of a Carnot cycle"
7     }]
8 )

Multi-Step Planning

1 response = client.chat.completions.create(
2     model="o4-mini",
3     reasoning_effort="medium",
4     messages=[{
5         "role": "user",
6         "content": "Design a complete system architecture for a real-time collaborative document editor"
7     }]
8 )

Tips for Best Results

Clearly state the problem and any constraints
Ask for step-by-step explanations when helpful
Use higher reasoning effort for truly complex problems
Consider token costs when choosing effort levels
Break extremely complex problems into smaller sub-problems