Models
For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending
.mdto the page URL.
Explore models available on the OpenAI API.
If you're not sure where to start, use GPT-5.6 Sol, our flagship model for complex reasoning and coding. Choose GPT-5.6 Terra to balance intelligence and cost, or GPT-5.6 Luna for cost-sensitive, high-volume workloads.
All latest OpenAI models support text and image input, text output, multilingual capabilities, and vision. Models are available via the Responses API and our Client SDKs.
Recommended models
- GPT-5.6 Sol: Start here for complex reasoning and coding.
- GPT-5.6 Terra: Balance intelligence and cost.
- GPT-5.6 Luna: Optimize cost-sensitive, high-volume workloads.
Browse our full catalog of models
Diverse models for a variety of tasks
See how OpenAI uses your data and review deprecated models.
- babbage-002: Replacement for the GPT-3 ada and babbage base models
- Chat Latest: Latest Instant model used in ChatGPT
- ChatGPT-4o: GPT-4o model used in ChatGPT
- chatgpt-image-latest: Previous image model used in ChatGPT.
- codex-mini-latest: Fast reasoning model optimized for the Codex CLI
- computer-use-preview: Specialized model for computer use tool
- DALL·E 2: Our first image generation model
- DALL·E 3: Previous generation image generation model
- davinci-002: Replacement for the GPT-3 curie and davinci base models
- GPT Image 1: Our previous image generation model
- GPT Image 1.5: Our previous image generation model
- GPT Image 2: State-of-the-art image generation model
- GPT Live Transcribe: Low-latency speech-to-text model for realtime transcription
- GPT Transcribe: High-accuracy speech-to-text model for file and Realtime input transcription
- GPT-3.5 Turbo: Legacy GPT model for cheaper chat and non-chat tasks
- gpt-3.5-turbo-16k-0613: Legacy GPT model for cheaper chat and non-chat tasks
- gpt-3.5-turbo-instruct: An older model only compatible with the legacy Completions endpoint
- GPT-4: An older high-intelligence GPT model
- GPT-4 Turbo: An older high-intelligence GPT model
- GPT-4 Turbo Preview: An older fast GPT model
- 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
- GPT-4.5 Preview: Deprecated large 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 mini Search Preview: Fast, affordable small model for web search
- 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 Realtime: Model capable of realtime text and audio inputs and outputs
- GPT-4o Search Preview: GPT model for web search in Chat Completions
- 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: Previous intelligent reasoning model for coding and agentic tasks with configurable reasoning effort
- GPT-5 Chat: GPT-5 model used in ChatGPT
- GPT-5 mini: Near-frontier intelligence for cost sensitive, low latency, high volume workloads
- GPT-5 nano: Fastest, most cost-efficient version of GPT-5
- GPT-5 Pro: Version of GPT-5 that produces smarter and more precise responses
- GPT-5-Codex: A version of GPT-5 optimized for agentic coding in Codex
- GPT-5.1: The best model for coding and agentic tasks with configurable reasoning effort
- GPT-5.1 Chat: GPT-5.1 model used in ChatGPT
- GPT-5.1-Codex: A version of GPT-5.1 optimized for agentic coding in Codex.
- GPT-5.1-Codex mini: Smaller, more cost-effective, less-capable version of GPT-5.1-Codex
- GPT-5.1-Codex-Max: A version of GPT-5.1-codex optimized for long running tasks.
- GPT-5.2: Previous frontier model for professional work with configurable reasoning effort
- GPT-5.2 Chat: GPT-5.2 model used in ChatGPT
- GPT-5.2 Pro: Previous pro model for professional work that produces smarter and more precise responses.
- GPT-5.2-Codex: Our most intelligent coding model optimized for long-horizon, agentic coding tasks.
- GPT-5.3 Chat: GPT-5.3 Instant model used in ChatGPT
- GPT-5.3-Codex: The most capable agentic coding model to date.
- GPT-5.4: A more affordable model for coding and professional work.
- GPT-5.4 mini: Our strongest mini model yet for coding, computer use, and subagents
- GPT-5.4 nano: Our cheapest GPT-5.4-class model for simple high-volume tasks
- GPT-5.4 Pro: Version of GPT-5.4 that produces smarter and more precise responses.
- 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-5.6 Luna: GPT-5.6 model optimized for cost-sensitive workloads
- GPT-5.6 Sol: Frontier model for complex professional work
- GPT-5.6 Terra: GPT-5.6 model that balances intelligence and cost
- gpt-audio: For audio inputs and outputs with Chat Completions API
- gpt-audio-1.5: The best voice model for audio in, audio out with Chat Completions.
- gpt-audio-mini: A cost-efficient version of GPT Audio
- gpt-image-1-mini: A cost-efficient version of GPT Image 1
- gpt-oss-120b: Most powerful open-weight model, fits into an H100 GPU
- gpt-oss-20b: Medium-sized open-weight model for low latency
- GPT-Realtime: Model capable of realtime text and audio inputs and outputs
- GPT-Realtime mini: A cost-efficient version of GPT-Realtime
- GPT-Realtime-1.5: The best voice model for audio in, audio out
- GPT-Realtime-2: Reasoning model with tool use
- GPT-Realtime-2.1: Reasoning model with tool use
- GPT-Realtime-2.1 mini: Reasoning model with tool use
- GPT-Realtime-Translate: Streaming speech-to-speech translation model
- GPT-Realtime-Whisper: Streaming speech-to-text model for realtime transcription
- o1: Previous full o-series reasoning model
- o1 Preview: Preview of our first o-series reasoning model
- o1-mini: A small model alternative to o1
- o1-pro: Version of o1 with more compute for better responses
- o3: Reasoning model for complex tasks, succeeded by GPT-5
- o3-deep-research: Our most powerful deep research model
- o3-mini: A small model alternative to o3
- o3-pro: Version of o3 with more compute for better responses
- o4-mini: Fast, cost-efficient reasoning model, succeeded by GPT-5 mini
- o4-mini-deep-research: Faster, more affordable deep research model
- omni-moderation: Identify potentially harmful content in text and images
- Sora 2: Flagship video generation with synced audio
- Sora 2 Pro: Most advanced synced-audio video generation
- text-embedding-3-large: Most capable embedding model
- text-embedding-3-small: Small embedding model
- text-embedding-ada-002: Older embedding model
- text-moderation: Previous generation text-only moderation model
- text-moderation-stable: 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