LLM·Dex
ProprietaryOpenAImidtext

o3-mini

Smaller, faster reasoning model, popular as the budget thinking-model option throughout 2025.

Updated


Quick facts

Released
Jan 2025
Context
200K tokens
Output / 1M
$4.40 / 1M tokens
License
Proprietary

About o3-mini

o3-mini was the practical entry point to reasoning models for many teams: cheap enough to run in production, smart enough to outperform GPT-4o on most reasoning-heavy tasks. It has been largely replaced by o4-mini for new workloads but remains widely deployed.

Benchmarks

Published scores from OpenAI's model card or independent leaderboards. We do not publish numbers we cannot source, see methodology.

HumanEval
,
Python coding pass@1
MMLU
,
Broad academic knowledge
GPQA
79.7
Graduate-level reasoning
SWE-bench
,
Real software-engineering tasks
  • GPQA79.7

Capabilities

Strengths

  • Reasoning at mid-tier cost
  • Fast for a thinking model

Tracked weaknesses

  • No vision support
  • Superseded by o4-mini for new builds

Pricing

Per-million-token rates as published by OpenAI.

TierPriceNotes
Input$1.10 / 1M tokensTokens you send to the model
Output$4.40 / 1M tokensTokens the model generates
Context200K tokensMax combined input + output

Call o3-mini from your code

Drop-in snippet for the OpenAI SDK. Set your API key in the environment and run.

typescript
import OpenAI from "openai";

const client = new OpenAI({
  // Use OPENAI_API_KEY for OpenAI, or your provider's key + baseURL.
  apiKey: process.env.OPENAI_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "o3-mini",
  messages: [
    { role: "user", content: "What's the time complexity of quicksort?" },
  ],
});

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

Compare o3-mini with…

Frequently asked

  • How much does o3-mini cost per million tokens?
    o3-mini is priced at $1.10 / 1M tokens for input tokens and $4.40 / 1M tokens for output tokens via the official OpenAI API at the time of writing.
  • What is o3-mini's context window?
    o3-mini supports a context window of 200K tokens.
  • Is o3-mini open source?
    No. o3-mini is a closed-weight model, you can use it via OpenAI's API but the model weights are not publicly downloadable.
  • When was o3-mini released?
    o3-mini was released on Jan 31, 2025 by OpenAI.
  • What is o3-mini's knowledge cutoff?
    o3-mini's training data has a knowledge cutoff of Oct 2023. For information after that date you'll need a tool-use or web-search wrapper.
Friday digest

Intelligence, distilled weekly.

One short email every Friday, new model launches, leaderboard moves, and pricing drops. Curated by hand. Free, no spam.