Models
Explore all available models and compare their capabilities.
Featured models
Frontier models
OpenAI's most advanced models, recommended for most tasks.
GPT-5.2
The best model for coding and agentic tasks across industries
GPT-5 mini
A faster, cost-efficient version of GPT-5 for well-defined tasks
GPT-5 nano
Fastest, most cost-efficient version of GPT-5
GPT-5.2 pro
Version of GPT-5.2 that produces smarter and more precise responses.
GPT-5
Previous intelligent reasoning model for coding and agentic tasks with configurable reasoning effort
GPT-4.1
Smartest non-reasoning model
Open-weight models
Open-weight models under a permissive Apache 2.0 license.
Specialized models
Purpose-built for specific tasks.
Sora 2
Flagship video generation with synced audio
Sora 2 Pro
Most advanced synced-audio video generation
o3-deep-research
Our most powerful deep research model
o4-mini-deep-research
Faster, more affordable deep research model
GPT Image 1
State-of-the-art image generation model
gpt-image-1-mini
A cost-efficient version of GPT Image 1
DALL·E 3
Deprecated
Previous generation image generation model
GPT-4o mini TTS
Text-to-speech model powered by GPT-4o mini
GPT-4o Transcribe
Speech-to-text model powered by GPT-4o
GPT-4o mini Transcribe
Speech-to-text model powered by GPT-4o mini
Realtime and audio models
Models for audio use cases and realtime inputs and outputs.
ChatGPT models
Models used in ChatGPT, not recommended for API use.
All models
Diverse models for a variety of tasks.
GPT-5.2
The best model for coding and agentic tasks across industries
GPT-5.1
The best model for coding and agentic tasks with configurable reasoning effort
GPT-5
Previous intelligent reasoning model for coding and agentic tasks with configurable reasoning effort
GPT-5 mini
A faster, cost-efficient version of GPT-5 for well-defined tasks
GPT-5 nano
Fastest, most cost-efficient version of GPT-5
GPT-5.1 Codex
A version of GPT-5.1 optimized for agentic coding in Codex.
GPT-5.1-Codex-Max
Our most intelligent coding model optimized for long-horizon, agentic coding tasks.
GPT-5-Codex
A version of GPT-5 optimized for agentic coding in Codex
GPT-5.2 pro
Version of GPT-5.2 that produces smarter and more precise responses.
GPT-5 pro
Version of GPT-5 that produces smarter and more precise responses
Sora 2
Flagship video generation with synced audio
Sora 2 Pro
Most advanced synced-audio video generation
GPT Image 1
State-of-the-art image generation model
gpt-image-1-mini
A cost-efficient version of GPT Image 1
o3-deep-research
Our most powerful deep research model
o4-mini-deep-research
Faster, more affordable deep research model
o3-pro
Version of o3 with more compute for better responses
gpt-audio
For audio inputs and outputs with Chat Completions API
gpt-realtime
Model capable of realtime text and audio inputs and outputs
gpt-realtime-mini
A cost-efficient version of GPT Realtime
gpt-audio-mini
A cost-efficient version of GPT Audio
o3
Reasoning model for complex tasks, succeeded by GPT-5
o4-mini
Fast, cost-efficient reasoning model, succeeded by GPT-5 mini
GPT-4.1
Smartest non-reasoning model
GPT-4.1 mini
Smaller, faster version of GPT-4.1
GPT-4.1 nano
Fastest, most cost-efficient version of GPT-4.1
o1-pro
Version of o1 with more compute for better responses
computer-use-preview
Specialized model for computer use tool
GPT-4o mini Search Preview
Fast, affordable small model for web search
GPT-4o Search Preview
GPT model for web search in Chat Completions
GPT-4.5 Preview (Deprecated)
Deprecated large model.
o3-mini
A small model alternative to o3
GPT-4o mini Audio
Smaller model capable of audio inputs and outputs
GPT-4o mini Realtime
Smaller realtime model for text and audio inputs and outputs
o1
Previous full o-series reasoning model
omni-moderation
Identify potentially harmful content in text and images
o1-mini
Deprecated
A small model alternative to o1
o1 Preview
Deprecated
Preview of our first o-series reasoning model
GPT-4o
Fast, intelligent, flexible GPT model
GPT-4o Audio
GPT-4o models capable of audio inputs and outputs
GPT-4o mini
Fast, affordable small model for focused tasks
GPT-4o mini Audio
Smaller model capable of audio inputs and outputs
GPT-4o mini Realtime
Smaller realtime model for text and audio inputs and outputs
GPT-4o Realtime
Model capable of realtime text and audio inputs and outputs
GPT-4 Turbo
An older high-intelligence GPT model
babbage-002
Deprecated
Replacement for the GPT-3 ada and babbage base models
ChatGPT-4o
GPT-4o model used in ChatGPT
GPT-5.1 Codex mini
Smaller, more cost-effective, less-capable version of GPT-5.1-Codex
codex-mini-latest
Deprecated
Fast reasoning model optimized for the Codex CLI
DALL·E 2
Deprecated
Our first image generation model
DALL·E 3
Deprecated
Previous generation image generation model
davinci-002
Deprecated
Replacement for the GPT-3 curie and davinci base models
GPT-3.5 Turbo
Legacy GPT model for cheaper chat and non-chat tasks
GPT-4
An older high-intelligence GPT model
GPT-4 Turbo Preview
Deprecated
An older fast GPT model
GPT-4o mini Transcribe
Speech-to-text model powered by GPT-4o mini
GPT-4o mini TTS
Text-to-speech model powered by GPT-4o mini
GPT-4o Transcribe
Speech-to-text model powered by GPT-4o
GPT-4o Transcribe Diarize
Transcription model that identifies who's speaking when
GPT-5.2 Chat
GPT-5.2 model used in ChatGPT
GPT-5.1 Chat
GPT-5.1 model used in ChatGPT
GPT-5 Chat
GPT-5 model used in ChatGPT
GPT Image 1
State-of-the-art image generation model
gpt-oss-120b
Most powerful open-weight model, fits into an H100 GPU
gpt-oss-20b
Medium-sized open-weight model for low latency
text-embedding-3-large
Most capable embedding model
text-embedding-3-small
Small embedding model
text-embedding-ada-002
Older embedding model
text-moderation
Deprecated
Previous generation text-only moderation model
text-moderation-stable
Deprecated
Previous generation text-only moderation model
TTS-1
Text-to-speech model optimized for speed
TTS-1 HD
Text-to-speech model optimized for quality
Whisper
General-purpose speech recognition model
