LLM·Dex
Newsletter
ProprietaryOpenAIflagshiptextvision

o3

OpenAI's flagship reasoning model, set the bar for hard math, GPQA, and agent benchmarks in 2025.

Updated

Quick facts

Released
Apr 2025
Context
200K tokens
Output / 1M
$8.00 / 1M tokens
License
Proprietary

About o3

o3 was the public release that established the reasoning-model paradigm as production-ready. Its scores on GPQA Diamond and ARC-AGI were the first that suggested LLMs could genuinely tackle graduate-level science questions and abstract reasoning puzzles in a controlled setting.

Despite GPT-5's unified-model approach absorbing much of o3's mindshare, o3 remains the model of choice for the most demanding reasoning workloads where wall-clock time isn't the constraint.

Benchmarks

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 We do not publish numbers we cannot source, see methodology.

HumanEval
95.0
Python coding pass@1
MMLU
,
Broad academic knowledge
GPQA
87.7
Graduate-level reasoning
SWE-bench
,
Real software-engineering tasks
  • HumanEval95.0
  • GPQA87.7

Capabilities

Strengths

  • Industry-leading reasoning depth at launch
  • Strong on math, science, and abstract puzzles
  • Tool-use during reasoning loops

Tracked weaknesses

  • Slow first-token, unpredictable total latency
  • Expensive when reasoning runs long

Pricing

Per-million-token rates as published by OpenAI.

TierPriceNotes
Input$2.00 / 1M tokensTokens you send to the model
Output$8.00 / 1M tokensTokens the model generates
Context200K tokensMax combined input + output

Call o3 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",
  messages: [
    { role: "user", content: "What's the time complexity of quicksort?" },
  ],
});

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

Best for

Tasks where o3 ranks among LLMDex's top picks.

Compare o3 with…

Frequently asked

  • How much does o3 cost per million tokens?
    o3 is priced at $2.00 / 1M tokens for input tokens and $8.00 / 1M tokens for output tokens via the official OpenAI API at the time of writing.
  • What is o3's context window?
    o3 supports a context window of 200K tokens.
  • Is o3 open source?
    No. o3 is a closed-weight model, you can use it via OpenAI's API but the model weights are not publicly downloadable.
  • When was o3 released?
    o3 was released on Apr 16, 2025 by OpenAI.
  • What is o3's knowledge cutoff?
    o3's training data has a knowledge cutoff of Jun 2024. 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.