All models
Official page
o3
frontierOpenAI
OpenAI's most powerful reasoning model. Excels at science, math, coding, and complex multi-step problems through deep chain-of-thought reasoning.
reasoningsciencemathcoding
Context
200K
Input / 1M
$2.00
Output / 1M
$8.00
Knowledge cutoff
2024-06
Capabilities
Code5/5
Reasoning5/5
Multilingual4/5
Safety4/5
Speed2/5
Modalities & Features
Vision (image input) Yes
Audio No
Video No
Function / tool calling Yes
JSON mode Yes
Extended thinking Yes
Context & Output
Context window200K
Max output tokens100K
Knowledge cutoff2024-06
Release date2025-04
API & Access
Open source No
Streaming Yes
Batch API Yes
Prompt caching No
Fine-tuning No
Benchmarks
MMLUGeneral knowledge
91.4%GPQA DiamondHard science Q&A
87.7%MATHMath problem solving
96.7%AIME 2025Advanced math
96.7%GSM8KGrade-school math
97.2%HumanEvalCode generation
92.8%LiveCodeBenchLive coding problems
N/ASWE-bench VerifiedReal-world software
69.1%HellaSwagCommonsense inference
N/ASource: provider technical reports & independent evaluations. N/A = not yet published for this model.
Pricing (per 1M tokens)
Input$2.00
Output$8.00
Consumer plan
ChatGPT Pro
$200/mo
Prices shown are list prices and may vary by provider plan. Always check official documentation for the latest pricing.