o3
Active83.5FrontierOpenAI's most powerful reasoning model, successor to o1.
Intelligence Index
83.5/ 100
Frontierweighted across 7 benchmarks
- Math
- 97.3
- Reasoning
- 87.7
- General knowledge
- 86.1
- Coding
- 62.8
Computed as the mean of per-category averages across MMLU, GPQA, SWE-bench, HumanEval, MATH, GSM8K, AIME, Aider Polyglot and more. See each benchmark for methodology.
Overview
o3 is OpenAI's top-tier reasoning model trained with reinforcement learning on chain-of-thought. It leads on AIME, GPQA, and SWE-bench across all published models as of mid-2025.
History
o3 became available via the OpenAI API on 2025-04-16.
Training & availability
Training data has a knowledge cutoff of 2024-06-30 — information about events after that date is unlikely to appear in the model's responses. OpenAI has not released the underlying model weights — access is via their hosted API only.
Capabilities
-
Context window: 200K tokens.
-
Max output: 100K tokens.
-
Input modalities: text, image.
-
Intelligence Index: 83.5/100.
Strongest categories: Math (97), Reasoning (88), General knowledge (86).
Recommended for: vision, math, agentic, long-context, frontier, reasoning.
Limitations
- The knowledge cutoff is 21 months old — this model will not know about recent events, releases, or API changes.
Pricing
- Input: $2.0000 per 1M tokens
- Output: $8.0000 per 1M tokens
Use the cost calculator above to estimate monthly spend for your workload.
Quick start
Minimal example using the openai API. Copy, paste, replace the key.
from openai import OpenAI
client = OpenAI(api_key="sk-...")
resp = client.chat.completions.create(
model="o3",
messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)Cost calculator
Estimate your monthly bill. Presets are typical workload sizes.
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| AIME 2024Math | 96.7% accuracy | Self-reported OpenAI o3 system card |
| Aider PolyglotCoding | 53.8% pass@2 | Third-party Papers With Code |
| GPQA DiamondReasoning | 87.7% accuracy | Self-reported OpenAI o3 system card |
Integrations & tooling support
- Tool calling
- Supported
- Structured outputs
- Supported
Price vs quality
Strong performance at mid-tier pricing.
- Quality percentile
- 89.9%
- Effective price
- $6.5/1M
- Pricing breakdown
- $2/1M in
$8/1M out
Community ratings
Rate o3
Sign in to rate and review.
Comments
Sign in to leave a comment.