Every model.
One key.

Amazon Nova Sonic V1 - ultra-low latency model for real-time applications.

Mistral AI Pixtral Large (25.02)

Moonshot AI Kimi K2.5

DeepSeek DeepSeek-R1

Z.AI GLM 5

Amazon Nova Lite

Amazon Nova Micro V1 - compact model for fast inference and cost efficiency.

Amazon Titan Image Generator V2 - advanced text-to-image generation.

Anthropic Claude 3 Haiku

Anthropic Claude 3 Sonnet

Cohere Embed v4

Google Gemma 3 12B IT

Google Gemma 3 27B PT

Google Gemma 3 4B IT

Meta Llama 4 Maverick 17B Instruct

Meta Llama 4 Scout 17B Instruct

Mistral AI Mistral Large 3

Qwen Qwen3 VL 235B A22B

Writer Writer Palmyra Vision 7B

DeepSeek DeepSeek V3.2

Meta Llama 3.1 70B Instruct

Meta Llama 3.1 8B Instruct

Meta Llama 3.3 70B Instruct

Meta Llama 3 70B Instruct

Meta Llama 3 8B Instruct

MiniMax MiniMax M2

MiniMax MiniMax M2.1

MiniMax MiniMax M2.5

Mistral AI Devstral 2 123B

Mistral AI Mistral 7B Instruct

Mistral AI Mistral Small (24.02)

Mistral AI Mixtral 8x7B Instruct

Moonshot AI Kimi K2 Thinking

NVIDIA Nemotron Nano 3 30B

OpenAI GPT-OSS 120B - large open source model with 120 billion parameters.

OpenAI GPT-OSS 20B - open source model with 20 billion parameters.

OpenAI GPT OSS Safeguard 120B

OpenAI GPT OSS Safeguard 20B

Qwen Qwen3 235B A22B 2507

Qwen Qwen3 32B (dense)

Qwen Qwen3-Coder-30B-A3B-Instruct

Qwen Qwen3 Coder 480B A35B Instruct

Qwen Qwen3 Coder Next

Qwen Qwen3 Next 80B A3B

Z.AI GLM 4.7

Z.AI GLM 4.7 Flash

OpenAI GPT Realtime model - for real-time audio and voice applications.

GPT-Realtime-1.5 is our flagship audio model for voice agents and customer support.

GPT-Realtime-2 is our most capable realtime voice model. It supports speech-to-speech interactions with configurable reasoning effort, stronger instruction following, and more reliable tool use for complex voice-agent workflows.

GPT-Realtime-2.1 updates GPT-Realtime-2 with improved alphanumeric recognition, silence and noise handling, and interruption behavior. It supports speech-to-speech interactions with configurable reasoning effort, instruction following, and tool use for complex voice-agent workflows.

OpenAI GPT-4o Mini Transcribe - efficient speech-to-text model.

OpenAI GPT-4o Transcribe - speech-to-text transcription model.

OpenAI GPT-4o Transcribe Diarize - transcription with speaker diarization.

OpenAI GPT Audio model - specialized for speech understanding and audio processing.

The gpt-audio model is our first generally available audio model. It accepts audio inputs and outputs, and can be used in the Chat Completions REST API.

chat-latest points to the latest Instant model currently used in ChatGPT. We recommend leveraging GPT-6 Astra for production API usage. Learn more on the Model guidance page. The underlying model snapshot will be regularly updated.

ChatGPT Image Latest - current image generation model for ChatGPT integration.

OpenAI GPT-4.1 - improved model with enhanced reasoning and coding capabilities.

OpenAI GPT-5 base model - next generation for professional work.

GPT-5 Pro uses more compute to think harder and provide consistently better answers.

GPT-5.1 is our flagship model for coding and agentic tasks with configurable reasoning and non-reasoning effort. Learn more in our GPT-5.1 model guidance. Reasoning.effort supports: none (default), low, medium, and high.

OpenAI GPT-5.2 - optimized variant with improved efficiency.

OpenAI GPT-5.2 Pro - enhanced professional variant with extended capabilities.

GPT-5.3-Codex is optimized for agentic coding tasks in Codex or similar environments. GPT-5.3-Codex supports low, medium, high, and xhigh reasoning effort settings. If you want to learn more about prompting GPT-5.3-Codex, refer to our dedicated guide.

OpenAI frontier model for complex professional work across agentic, coding, and professional workflows.

GPT-5.4 Mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads. Learn more in our Model guidance page. Reasoning.effort supports: none (default), low, medium, high and xhigh.

GPT-5.4 Pro uses more compute to think harder and provide consistently better answers.

GPT-5.5 is a flagship model for the most complex professional work. Learn more in our GPT-5.5 model guidance. Reasoning.effort supports: none, low, medium (default), high and xhigh.

GPT-5.5 Pro uses more compute to think harder and provide consistently better answers.

An alias for our most advanced purpose-trained cybersecurity models, for approved defenders conducting advanced, authorized vulnerability research, exploit validation, and security testing.

GPT-5.6 Sol is a flagship model in the GPT-5.6 family. It roughly corresponds to the unsuffixed model tier used in earlier GPT-5 families. The gpt-5.6 alias routes requests to GPT-5.6 Sol. Reasoning.effort supports: none, low, medium (default), high, xhigh, and max.

GPT-5.6 Terra is designed for workloads that balance intelligence and cost. It roughly corresponds to the mini model tier used in earlier GPT-5 families. Reasoning.effort supports: none, low, medium (default), high, xhigh, and max.

GPT-6 Astra is our most capable model, built for the hardest end-to-end work. Use it for complex reasoning, coding, computer use, research, and document creation. reasoning.effort supports low, medium, high, xhigh, and max.

GPT-6 Sol is built for complex coding and agentic workflows.

OpenAI GPT Image 1 - original image generation model.

OpenAI GPT Image 1 Mini - efficient image generation for lightweight applications.

OpenAI GPT Image 1.5 - enhanced image generation model.

GPT Image 2 is our state-of-the-art image generation model for fast, high-quality image generation and editing. It supports flexible image sizes and high-fidelity image inputs. Learn more in our image generation guide, or see the pricing page and image generation calculator for cost estimates.

GPT Image 2.5 Flare is our fastest model for high-quality, everyday image generation. It accepts text and image inputs and produces image outputs. It supports low, medium, high, xhigh, max, and auto quality settings. Select it directly in the Image API or as the model of the Responses API image generation tool. Learn more in the image generation guide.

GPT Image 2.5 Sunburst generates and edits images from text and image inputs. Use it for workflows where editing precision matters most. It supports low, medium, high, xhigh, max, and auto quality settings. Select it directly in the Image API or as the model of the Responses API image generation tool. Learn more in the image generation guide.

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images.

The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers.

OpenAI GPT-4o Mini - highly efficient multimodal model.

GPT-Realtime-2.1 Mini is a distilled reasoning model for faster, lower-cost realtime voice interactions. It supports audio and text inputs over WebRTC, WebSocket, or SIP connections and improves alphanumeric recognition over GPT-Realtime-2.

OpenAI GPT Realtime Mini - compact model for real-time audio applications.

OpenAI GPT-4o Mini TTS - text-to-speech voice generation.

OpenAI GPT Audio Mini - efficient audio processing model.

TTS is a model that converts text to natural sounding spoken text. The tts-1 model is optimized for realtime text-to-speech use cases. Use it with the Speech endpoint in the Audio API.

TTS is a model that converts text to natural sounding spoken text. The tts-1-hd model is optimized for high quality text-to-speech use cases. Use it with the Speech endpoint in the Audio API.

OpenAI GPT-4.1 Mini - cost-efficient variant with solid capabilities.

OpenAI GPT-4.1 Nano - ultra-efficient model for lightweight applications.

OpenAI GPT-5 Mini - cost-efficient variant for general tasks.

OpenAI GPT-5 Nano - ultra-efficient model for edge and embedded applications.

GPT-5.4 nano is designed for tasks where speed and cost matter most like classification, data extraction, ranking, and sub-agents. Learn more in our Model guidance page. Reasoning.effort supports: none (default), low, medium, high and xhigh.

GPT-5.6 Luna is designed for cost-sensitive, high-volume workloads. It roughly corresponds to the nano model tier used in earlier GPT-5 families. Reasoning.effort supports: none, low, medium (default), high, xhigh, and max.

GPT-6 Luna is our most efficient model for focused, high-volume tasks.

Moderation models are free models designed to detect harmful content. This model is our most capable moderation model, accepting images as input as well. You can find the model card here.

OpenAI text-embedding-3-large - high dimensional embeddings for semantic search.

OpenAI text-embedding-3-small - efficient embeddings for fast similarity search.

text-embedding-ada-002 is our improved, more performant version of our ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.

Gemini 2.5 Pro - advanced multimodal model for enterprise applications.