o3
PremiumOpenAI's most powerful reasoning model — top across math, coding, and science.
Sets new standards for STEM problem solving with deep thinking capabilities. Also excels at technical writing, visual reasoning, and instruction following.
▼
o3 by OpenAI has a Capability Index of 79.2, making it comparable to the field average. It ranks #27 out of 92 models on the idapt capability leaderboard. It resolves 62% of SWE-bench Verified coding tasks. o3 is competitively priced at $2.00/M tokens input and $8.00/M tokens output. Cached input reads are priced at $0.50/M tokens, making repeated context cheaper. The model supports vision/image input, extended reasoning, a 200K context window.
o1Benchmarks
Category Rankings
Specifications
Performance
Providers
Misc
Compare with
GPT 5.6 Solvs o3GPT 5.6 Lunavs o3
Claude Fable 5vs o3Claude Opus 4.8vs o3Claude Sonnet 5vs o3Claude Haiku 4.5vs o3
Gemini 3.6 Flashvs o3Gemini 3.5 Flashvs o3Gemini 3.5 Flash-Litevs o3Gemma 4 31Bvs o3
Grok 4.5vs o3Grok Build 0.1vs o3Grok 4.1 Fastvs o3
Muse Spark 1.1vs o3
DeepSeek V4 Provs o3DeepSeek V4 Flashvs o3
MiniMax M3vs o3
GLM 5.2vs o3
Qwen3.7 Maxvs o3Qwen3.7 Plusvs o3Qwen3 Coder Nextvs o3
Nemotron 3 Ultravs o3
Mistral Small 4vs o3Frequently Asked Questions about o3▼
When was o3 released?
▼
o3 was released on April 16, 2025.
Who created o3?
▼
o3 was created by OpenAI.
How capable is o3?
▼
o3 has a Capability Index of 79.2/100, making it comparable to the field average. It ranks #27 out of 92 models.
How much does o3 cost?
▼
o3 costs $2.00/M input tokens and $8.00/M output tokens.
What is o3 API pricing?
▼
The o3 API is priced at $2.00 per million input tokens and $8.00 per million output tokens. You can access o3 through idapt.app alongside 200+ other AI models in one workspace.
Is o3 a reasoning model?
▼
Yes, o3 is a reasoning model. It can think step-by-step through complex problems before providing an answer, often yielding better results on difficult tasks like math, coding, and multi-step logic.
Does o3 support image or vision input?
▼
Yes, o3 supports vision/image input. You can share images in your conversation and the model will analyze and respond based on their content.
Does o3 support audio?
▼
No, o3 does not support audio input.
What is the context window of o3?
▼
o3 has a context window of 200K tokens, meaning it can process approximately 150,000 words of context at once.
Is o3 open source?
▼
o3 is a proprietary model developed by OpenAI. The model weights and training data are not publicly available.
How does o3 perform on coding?
▼
o3 resolves 62% of SWE-bench Verified tasks — real GitHub issues fixed end-to-end, the strongest single signal for agentic software engineering.
What is o3 good at?
▼
Based on benchmark data, o3 excels at: software development and coding tasks, mathematical problem solving, visual analysis and image understanding. It is OpenAI's capable model suitable for a wide range of tasks.
Where can I use o3?
▼
You can chat with o3 on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access o3 through OpenAI's own API or platform.