All models
For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending
.mdto the page URL.
Browse models and compare their capabilities.
Flagship models
Compare capabilities and specifications.
- GPT-6 Astra: Our most capable model for the most demanding work.
- GPT-6.1 Sol: Near-Astra performance for complex work at a lower cost.
- GPT-6.1 Terra: A fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.
- GPT-6 Luna: Our most efficient model for focused, high-volume tasks.
Image
Models for image generation and editing.
- GPT-Image-2.5 Sunburst: Our most capable model for image generation and editing
- GPT-Image-2.5 Flare: Fast, high-quality everyday image generation
- GPT-Image-2: State-of-the-art image generation model
Realtime & audio
Models for realtime, speech, and audio workflows.
- GPT-Live 1: Our premier model for natural, expressive voice conversations with smooth interruption handling.
- GPT-Realtime-2.1: Reasoning model with tool use
- GPT-Realtime-2.1 Mini: Reasoning model with tool use
- GPT-Realtime-2: Reasoning model with tool use
- GPT-Realtime-Translate: Streaming speech-to-speech translation model
- GPT-Live-Transcribe: Low-latency speech-to-text model for realtime transcription
- GPT-Realtime-Whisper: Streaming speech-to-text model for realtime transcription
- GPT-Realtime-1.5: The best voice model for audio in, audio out
- GPT-Audio-1.5: The best voice model for audio in, audio out with Chat Completions.
- GPT-Transcribe: High-accuracy speech-to-text model for file and Realtime input transcription
OpenAI Daybreak
Advanced cyber models for defenders
- GPT-5.6 Cyber: Our most advanced cybersecurity model for authorized vulnerability research and security testing.
Life sciences
Models for life sciences research
- GPT-Rosalind: Life sciences reasoning for approved organizations. Model ID:
gpt-rosalind-research.
Open-weight models
Open-weight models under a permissive Apache 2.0 license.
- gpt-oss-120b: Most powerful open-weight model, fits into an H100 GPU
- gpt-oss-20b: Medium-sized open-weight model for low latency
Embedding models
Models for embedding text into vector representations.
- text-embedding-3-large: Most capable embedding model
- text-embedding-3-small: Small embedding model
- text-embedding-ada-002: Older embedding model
More models
Diverse models for a variety of tasks.
- GPT-6 Sol: Built to power complex coding and agentic workflows.
- GPT-5.6 Sol: GPT-5.6 flagship model for complex professional work
- GPT-5.6 Terra: GPT-5.6 model that balances intelligence and cost
- GPT-5.6 Luna: GPT-5.6 model optimized for cost-sensitive workloads
- GPT-5.5: A new class of intelligence for coding and professional work.
- GPT-5.5 Pro: Version of GPT-5.5 that produces smarter and more precise responses.
- GPT-5.4: A more affordable model for coding and professional work.
- GPT-5.4 Pro: Version of GPT-5.4 that produces smarter and more precise responses.
- GPT-5.4 Mini: Our strongest mini model yet for coding, computer use, and subagents
- GPT-5.2: Previous flagship model for professional work with configurable reasoning effort
- GPT-5.2 Pro: Previous pro model for professional work that produces smarter and more precise responses.
- omni-moderation: Identify potentially harmful content in text and images
ChatGPT models
Models used in ChatGPT, not recommended for API use.
- Chat Latest: Latest Instant model used in ChatGPT
Deprecated models
Includes models that have already shut down.
- GPT-Image-1.5: Deprecated. Our previous image generation model
- chatgpt-image-latest: Deprecated. Previous image model used in ChatGPT.
- GPT-Image-1: Shut down. Retired image generation model
- GPT-Image-1 Mini: Deprecated. A cost-efficient version of GPT Image 1
- GPT-Realtime: Deprecated. Model capable of realtime text and audio inputs and outputs
- GPT-Audio: Deprecated. For audio inputs and outputs with Chat Completions API
- GPT-4o Transcribe: Deprecated. Speech-to-text model powered by GPT-4o
- GPT-4o Mini Transcribe: Deprecated. Speech-to-text model powered by GPT-4o Mini
- GPT-4o Transcribe Diarize: Deprecated. Transcription model that identifies who's speaking when
- TTS-1: Deprecated. Text-to-speech model optimized for speed
- TTS-1 HD: Deprecated. Text-to-speech model optimized for quality
- Whisper: Deprecated. General-purpose speech recognition model
- GPT-Realtime Mini: Deprecated. A cost-efficient version of GPT-Realtime
- GPT-Audio Mini: Deprecated. A cost-efficient version of GPT Audio
- GPT-4o Audio: Shut down. GPT-4o models capable of audio inputs and outputs
- GPT-4o Mini Audio: Shut down. Smaller model capable of audio inputs and outputs
- GPT-4o Realtime: Shut down. Model capable of realtime text and audio inputs and outputs
- GPT-4o Mini Realtime: Shut down. Smaller realtime model for text and audio inputs and outputs
- GPT-4o Mini TTS: Deprecated. Text-to-speech model powered by GPT-4o Mini
- Daybreak Red: Deprecated. An alias for advanced cybersecurity models for authorized vulnerability research and security testing.
- Daybreak Blue: Deprecated. An alias for flagship general-purpose models with safeguards for defensive cybersecurity work.
- GPT-5.4 nano: Deprecated. Our cheapest GPT-5.4-class model for simple high-volume tasks
- GPT-5.3-Codex: Deprecated. The most capable agentic coding model to date.
- GPT-5.1: Deprecated. The best model for coding and agentic tasks with configurable reasoning effort
- GPT-5: Deprecated. Previous intelligent reasoning model for coding and agentic tasks with configurable reasoning effort
- GPT-5 Mini: Deprecated. Strong intelligence for cost sensitive, low latency, high volume workloads
- GPT-5 nano: Deprecated. Fastest, most cost-efficient version of GPT-5
- GPT-5 Pro: Deprecated. Version of GPT-5 that produces smarter and more precise responses
- o3-pro: Deprecated. Version of o3 with more compute for better responses
- o3: Deprecated. Reasoning model for complex tasks, succeeded by GPT-5
- GPT-4.1: Deprecated. Smartest non-reasoning model
- GPT-4.1 Mini: Deprecated. Smaller, faster version of GPT-4.1
- GPT-4o Mini: Deprecated. Fast, affordable small model for focused tasks
- GPT-5.3 Chat: Shut down. GPT-5.3 Instant model used in ChatGPT
- GPT-5.2 Chat: Shut down. GPT-5.2 model used in ChatGPT
- GPT-5.2-Codex: Shut down. Our most intelligent coding model optimized for long-horizon, agentic coding tasks.
- o3-deep-research: Shut down. Our most powerful deep research model
- o4-mini-deep-research: Shut down. Faster, more affordable deep research model
- GPT-4.1 nano: Shut down. Fastest, most cost-efficient version of GPT-4.1
- o4-mini: Shut down. Fast, cost-efficient reasoning model, succeeded by GPT-5 Mini
- o1-pro: Shut down. Version of o1 with more compute for better responses
- computer-use-preview: Shut down. Specialized model for computer use tool
- GPT-4o Mini Search Preview: Shut down. Fast, affordable small model for web search
- GPT-4o Search Preview: Shut down. GPT model for web search in Chat Completions
- GPT-4.5 Preview: Shut down. Deprecated large model.
- o3-mini: Shut down. A small model alternative to o3
- o1: Shut down. Previous full o-series reasoning model
- o1-mini: Shut down. A small model alternative to o1
- o1 Preview: Shut down. Preview of our first o-series reasoning model
- GPT-4o: Deprecated. Fast, intelligent, flexible GPT model
- GPT-4 Turbo: Shut down. An older high-intelligence GPT model
- babbage-002: Shut down. Replacement for the GPT-3 ada and babbage base models
- ChatGPT-4o: Shut down. GPT-4o model used in ChatGPT
- GPT-5.1-Codex: Shut down. A version of GPT-5.1 optimized for agentic coding in Codex.
- GPT-5.1-Codex-Max: Shut down. A version of GPT-5.1-codex optimized for long running tasks.
- GPT-5.1-Codex Mini: Shut down. Smaller, more cost-effective, less-capable version of GPT-5.1-Codex
- GPT-5-Codex: Shut down. A version of GPT-5 optimized for agentic coding in Codex
- codex-mini-latest: Shut down. Fast reasoning model optimized for the Codex CLI
- davinci-002: Shut down. Replacement for the GPT-3 curie and davinci base models
- GPT-3.5 Turbo: Shut down. Legacy GPT model for cheaper chat and non-chat tasks
- GPT-4: Shut down. An older high-intelligence GPT model
- GPT-4 Turbo Preview: Shut down. An older fast GPT model
- GPT-5.1 Chat: Shut down. GPT-5.1 model used in ChatGPT
- GPT-5 Chat: Shut down. GPT-5 model used in ChatGPT
- text-moderation: Shut down. Previous generation text-only moderation model
- text-moderation-stable: Shut down. Previous generation text-only moderation model