o3-mini-high

Neural Network

GPT o3 mini high is a new, efficient solution for fast coding, complex mathematical tasks, and scientific research. The model was launched by OpenAI at the end of January 2025 and combines high accuracy with an affordable price. It helps automate routine processes and saves users time.

Main

/

Models

/

o3-mini-high
100 000

Max answer length

(in tokens)

200 000

Context size

(in tokens)

1,1 $

Prompt cost

(per 1M tokens)

4,4 $

Answer cost

(per 1M tokens)

0 $

Image prompt

(per 1K tokens)

Overview
Providers
API
bothub
BotHub: Try GPT Chat for Freebot

Caps remaining: 0 CAPS
Providers o3-mini-highOn Bothub, you can select your own providers for requests. If you haven't made a selection, we will automatically find suitable providers who can handle the size and parameters of your request.
Code example and API for o3-mini-highWe offer full access to the OpenAI API through our service. All our endpoints fully comply with OpenAI endpoints and can be used both with plugins and when developing your own software through the SDK.Create API key
Javascript
Python
Curl
import OpenAI from 'openai';
const openai = new OpenAI({
  apiKey: '<your bothub access token>',
  baseURL: 'https://bothub.chat/api/v2/openai/v1'
});


// Sync - Text generation 

async function main() {
  const chatCompletion = await openai.chat.completions.create({
    messages: [{ role: 'user', content: 'Say this is a test' }],
    model: 'o3-mini-high',
  });
} 

// Async - Text generation 

async function main() {
  const stream = await openai.chat.completions.create({
    messages: [{ role: 'user', content: 'Say this is a test' }],
    model: 'o3-mini-high',
    stream: true
  });

  for await (const chunk of stream) {
    const part: string | null = chunk.choices[0].delta?.content ?? null;
  }
} 
main();
illustaration

How it works o3-mini-high?

Among its key strengths are impressive accuracy in programming (49.3% on the SWE-bench Verified test) and high results in mathematics (87.3% on AIME 2024). The model is capable of solving scientific problems with 79.7% accuracy according to GPQA Diamond and offers advanced chain-of-thought logic to accelerate solution finding. GPT o3 mini high operates 3.26 times faster than o3 mini and costs around $1.15 per million tokens.