o3-mini
OpenAI's reasoning model optimized for STEM tasks, coding, and math. Uses chain-of-thought reasoning.
Examples
See what o3-mini can generate
Prove that the square root of 2 is irrational
Assume for contradiction that sqrt(2) is rational, meaning sqrt(2) = p/q where p and q are integers with no common factors. Squaring both sides gives 2 = p²/q², so p² = 2q². This means p² is even, which implies p is even—write p = 2k. Substituting gives 4k² = 2q², so q² = 2k², meaning q is also even. But if both p and q are even, they share a common factor of 2, contradicting our assumption. Therefore sqrt(2) must be irrational.
Three boxes are labeled 'Apples', 'Oranges', and 'Mixed'. All labels are wrong. You can pick one fruit from one box. How do you determine the correct labels?
Pick a fruit from the box labeled 'Mixed'. Since all labels are wrong, this box contains only one type of fruit—either all apples or all oranges. Say you draw an apple: the 'Mixed' box is actually the Apples box. Now consider the remaining two boxes labeled 'Apples' and 'Oranges'. The box labeled 'Apples' cannot be apples (wrong label) and cannot be mixed (we found that), so it must be Oranges. The box labeled 'Oranges' is therefore the Mixed box. One draw is all you need.
0.7
Response will appear here...
Pricing
API Integration
Use our OpenAI-compatible API to integrate o3-mini into your application.
npm install railwailimport railwail from "railwail";
const rw = railwail("YOUR_API_KEY");
// Simple — just pass a string
const reply = await rw.run("o3-mini", "Hello! What can you do?");
console.log(reply);
// With message history
const reply2 = await rw.run("o3-mini", [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);
// Full response with usage info
const res = await rw.chat("o3-mini", [
{ role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);Free credits on sign-up
Related Models
View all Text & ChatClaude Opus 4
Anthropic's most powerful model. Exceptional at complex analysis, agentic tasks, and extended reasoning.
Claude Sonnet 4
Anthropic's most capable model. Excellent for complex analysis, coding, math, and creative writing.
GPT-4.1
OpenAI's newest flagship model. Improved reasoning, instruction following, and coding over GPT-4o.
GPT-4.5 Preview
OpenAI's latest frontier model with improved reasoning, creativity, and instruction following. Significant improvements over GPT-4o.
Start using o3-mini today
Get started with free credits. No credit card required. Access o3-mini and 100+ other models through a single API.