OpenAI
California, 美国GPT 5.2 Mini is OpenAI's smaller, cost-efficient speech-to-text model built on GPT-4o Mini audio capabilities. It is a smaller-footprint option suited to tighter latency or deployment budgets.
o3 Preview is an announced preview model from OpenAI's o3 family. Public o3-family releases include [o3-mini](/openai/o3-mini) and [o3](/openai/o3).
Daybreak Blue is OpenAI's controlled-access alias for frontier general-purpose models with safeguards calibrated for defensive cybersecurity work.
Daybreak Red is OpenAI's controlled-access alias for its most advanced purpose-trained cybersecurity models for authorized vulnerability research, exploit validation, and security testing.
GPT 5.6 Cyber is OpenAI's cyber-focused GPT-5.6 variant for advanced, authorized cybersecurity work through the Daybreak Trusted Access for Cyber program.
A fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.
GPT Live 1.1 is an update to OpenAI's full-duplex GPT Live voice model for ChatGPT Voice, Codex and dots, adding 13 new voices across six non-English languages, better accents, more natural filler while it works and better instruction following. API access is coming soon.
GPT-6.1 Sol with OpenAI Pro reasoning mode for difficult tasks.
Near-Astra performance for complex coding, computer use, and professional work at a lower cost.
GPT-6 Luna Pro is the same underlying GPT-6 Luna model served with reasoning.mode set to pro for higher-quality responses on complex tasks.
GPT-6 Sol Pro is the same underlying GPT-6 Sol model served with reasoning.mode set to pro for higher-quality responses on complex tasks.
GPT Image 2.5 Flare is OpenAI's fast, high-quality default for everyday image generation and editing. Choose it when iteration speed matters; it supports reference-image and multi-turn edits, transparent backgrounds, custom dimensions up to 4K, and quality levels through max.
GPT Image 2.5 Sunburst is OpenAI's premium model for image generation and editing workflows where precision matters most. Choose it for tighter creative control, detailed production assets, campaign creative, and polished product imagery when the best result matters more than Flare's faster generation.
GPT-6 Astra Pro is the same underlying GPT-6 Astra model served with reasoning.mode set to pro for higher-quality responses on complex tasks.
GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation. It supports text and image input, a 1.05M-token context window, up to 128K output tokens, and low through max reasoning effort.
GPT Live Transcribe is OpenAI's low-latency streaming speech-to-text model for Realtime transcription sessions. It supports free-form context, keyword hints, and multiple language hints.
GPT Transcribe is OpenAI's high-accuracy speech-to-text model for completed audio files, streamed file transcripts, and committed Realtime turns. It supports free-form context, keyword hints, and multiple language hints.
GPT 5.6 Luna is OpenAI's fast and affordable GPT-5.6 model for lower-latency and cost-sensitive workloads.
GPT 5.6 Luna Pro is the same underlying GPT-5.6 Luna model served with reasoning.mode set to pro for higher-quality responses on complex tasks.
GPT 5.6 Sol is OpenAI's flagship GPT-5.6 model for advanced reasoning, agentic coding, scientific analysis, and complex professional work.
GPT 5.6 Sol Pro is the same underlying GPT-5.6 Sol model served with reasoning.mode set to pro for higher-quality responses on complex tasks.
GPT 5.6 Terra is OpenAI's balanced GPT-5.6 model for everyday work across reasoning, coding, and assistant workflows.
GPT 5.6 Terra Pro is the same underlying GPT-5.6 Terra model served with reasoning.mode set to pro for higher-quality responses on complex tasks.
GPT Live 1 is OpenAI's full-duplex voice model for ChatGPT Voice, designed for continuous bidirectional audio conversations that can listen, speak, pause, interrupt, and delegate deeper work while the conversation continues.
GPT Live 1 Mini is OpenAI's smaller GPT-Live voice model for ChatGPT Voice, designed for continuous bidirectional audio conversations with lower-cost default availability for Free users.
GPT Realtime 2.1 updates GPT Realtime 2 with improved alphanumeric recognition, silence and noise handling, interruption behavior, configurable reasoning effort, instruction following, and tool use for complex voice-agent workflows.
GPT Realtime 2.1 Mini is a distilled reasoning model for faster, lower-cost realtime voice interactions over WebRTC, WebSocket, or SIP connections, with improved alphanumeric recognition over GPT Realtime 2.
GPT Realtime 2 is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.
GPT Realtime Translate is a translation model from OpenAI for converting text between languages. It is aimed at multilingual translation and localization workflows.
GPT Realtime Whisper is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.
GPT 5.5 is OpenAI's frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks.
GPT 5.5 Pro is OpenAI's high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It supports up to 1.1M of input context for long documents, codebases, and agent workflows.
GPT Image 2 is an image generation model from OpenAI for visual creation workflows. It supports text and image inputs for generation, restyling, or edit-style workflows.
GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports up to 400K of input context for long documents, codebases, and agent workflows.
GPT 5.4 is an OpenAI model, released in March 2026, that unifies the Codex and GPT lines into a single system. It supports up to 1.1M of input context for long documents, codebases, and agent workflows.
GPT 5.4 Pro is OpenAI's Pro-tier model, released in March 2026, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks.
GPT Audio 1.5 is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.
GPT Realtime 1.5 is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.
GPT 5.3 Codex Spark is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.
GPT 5.2 is a frontier-grade model in the GPT-5 series released in December 2025, offering stronger agentic and long context perfomance compared to GPT-5.1. It accepts text and image inputs and produces text outputs.
GPT 5.2 Pro is OpenAI's Pro-tier model, released in December 2025, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It targets higher-capability workloads where depth, quality, or scale matter more than raw speed.
GPT 5 Codex Mini is a smaller and faster version of GPT-5.1-Codex. It is a smaller-footprint option suited to tighter latency or deployment budgets.
GPT OSS Safeguard 120b is a safety reasoning model from OpenAI built upon gpt-oss-20b. It is suited to input filtering, safety checks, and policy enforcement in LLM applications.
GPT OSS Safeguard 20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. It is suited to input filtering, safety checks, and policy enforcement in LLM applications.
GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...
[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...
GPT 5 Search API is trained to understand and execute web search queries. It is aimed at retrieval-heavy assistants, browsing, and research synthesis.
GPT OSS 120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.
GPT OSS 20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It accepts text inputs and produces text outputs.
OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...
GPT 4.1 is a large language model, released in April 2025, optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports up to 1.0M of input context for long documents, codebases, and agent workflows.
GPT 4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It supports up to 1.0M of input context for long documents, codebases, and agent workflows.
OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...
The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...
GPT 4o (2024-11-20) is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It accepts text and image inputs and produces text outputs.
Omni Moderation is a safety model from OpenAI for moderation, prompt filtering, and policy enforcement. It is suited to input filtering, safety checks, and policy enforcement in LLM applications.
The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/).
GPT-4o mini is an OpenAI model released in July 2024 after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their small model, it is many multiples more affordable...
GPT 4o Mini (2024-07-18) is an OpenAI model released in July 2024 after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. It is a smaller-footprint option suited to tighter latency or deployment budgets.
Text Embedding 3 Large is OpenAI's most capable embedding model for both english and non-english tasks. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
Text Embedding 3 Small is OpenAI's improved, more performant version of the ada embedding model. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost.
Text Embedding Ada 002 is OpenAI's legacy text embedding model. It is aimed at semantic search, retrieval, clustering, and RAG pipelines.
GPT 3 is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.
Whisper 3 is OpenAI's open-source automatic speech recognition model, available via API as `whisper-1`. It supports transcription and translation across 50+ languages from audio files up to 25 MB.
Whisper 3 Turbo is an optimized version of OpenAI's Whisper Large V3 speech recognition model, designed for speed and cost efficiency. It is tuned for lower latency and cost-sensitive production use.
Whisper Large V3 is OpenAI's open-source automatic speech recognition model offering both audio transcription and translation. It targets higher-capability workloads where depth, quality, or scale matter more than raw speed.
Whisper Large V3 Turbo is an optimized version of OpenAI's Whisper Large V3 speech recognition model, designed for speed and cost efficiency. It is tuned for lower latency and cost-sensitive production use.
Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalize to many datasets and domains without the need for fine-tuning. This is the English-only version of the Whisper Tiny model which was trained on the task of speech recognition.
GPT 5.4 Nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports up to 400K of input context for long documents, codebases, and agent workflows.
GPT 5.3 Codex is OpenAI's most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2.
GPT Image 1.5 is an image generation model from OpenAI for visual creation workflows. It supports text and image inputs for generation, restyling, or edit-style workflows.
GPT 4o Mini Transcribe (2025-12-15) is OpenAI's smaller, cost-efficient speech-to-text model built on GPT-4o Mini audio capabilities. It is suited to captioning, meeting notes, transcription, and speech analytics pipelines.
GPT 4o Mini TTS (2025-12-15) is OpenAI's cost-efficient text-to-speech model. It converts text input into natural-sounding audio output, supporting a variety of voices and tones.
A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.
A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.
GPT 5.1 is a frontier-grade model in the GPT-5 series released in November 2025, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5.
The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences.
GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by GPT-5 Mini, with GPT Image 1 Mini for efficient image generation.
GPT Audio is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.
GPT Realtime is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.
GPT 5 is OpenAI's most advanced model, offering major improvements in reasoning, code quality, and user experience. It supports up to 400K of input context for long documents, codebases, and agent workflows.
GPT 5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It supports up to 400K of input context for long documents, codebases, and agent workflows.
GPT 5 Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.
GPT 5 Pro is OpenAI's most advanced model, offering major improvements in reasoning, code quality, and user experience. It targets higher-capability workloads where depth, quality, or scale matter more than raw speed.
The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. It supports up to 200K of input context for long documents, codebases, and agent workflows.
The June 3, 2025 GPT-4o Audio Preview snapshot supports text and audio input and output through Chat Completions. OpenAI has deprecated the legacy audio family in favor of GPT Audio 1.5.
o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It supports up to 200K of input context for long documents, codebases, and agent workflows.
GPT 4.1 Nano is the fastest and cheapest model in the GPT-4.1 series. It supports up to 1.0M of input context for long documents, codebases, and agent workflows.
GPT 4o Mini Transcribe (2025-03-20) is OpenAI's smaller, cost-efficient speech-to-text model built on GPT-4o Mini audio capabilities. It is suited to captioning, meeting notes, transcription, and speech analytics pipelines.
GPT 4o Transcribe is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.
TTS 1 is a text-to-speech model from OpenAI for turning text into spoken audio. It is suited to narration, assistants, and spoken user interfaces.
TTS 1 HD is a text-to-speech model from OpenAI for turning text into spoken audio. It is suited to narration, assistants, and spoken user interfaces.
Whisper 1 is OpenAI's open-source automatic speech recognition model, available via API as `whisper-1`. It supports transcription and translation across 50+ languages from audio files up to 25 MB.
GPT 5.4 Cyber is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.
GPT 5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It accepts text and image inputs and produces text outputs.
GPT 5.2 Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It accepts text and image inputs and produces text outputs.
GPT 5.2 Chat is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It accepts text and image inputs and produces text outputs.
Sora 2 (2025-12-08) is a video generation model from OpenAI for prompt-driven clip and scene creation. It supports turning still images into animated clips as well as prompt-driven video workflows.
GPT 5.1 Codex Max was an OpenAI agentic coding model, released in November 2025, designed for long-running, high-context software development tasks. It targeted higher-capability workloads where depth, quality, or scale mattered more than raw speed.
GPT 5.1 Chat is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It accepts text and image inputs and produces text outputs.
GPT 5.1 Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It accepts text and image inputs and produces text outputs.
GPT 5.1 Codex Mini is a smaller and faster version of GPT-5.1-Codex. It is a smaller-footprint option suited to tighter latency or deployment budgets.
A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.
A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.
OpenAI's flagship video generation model, delivering production-quality video with physics-accurate motion, synchronized audio, and world-state persistence across shots.
Sora 2 (2025-09-30) is a video generation model from OpenAI for prompt-driven clip and scene creation. It supports turning still images into animated clips as well as prompt-driven video workflows.
GPT 5 Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It accepts text and image inputs and produces text outputs.
GPT 5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications. It supports up to 400K of input context for long documents, codebases, and agent workflows.
o3 Deep Research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.
o4 mini Deep Research is OpenAI's faster, more affordable deep research model-ideal for tackling complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.
The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences.
Codex Mini is a smaller and faster version of GPT-5.1-Codex. It supports up to 200K of input context for long documents, codebases, and agent workflows.
GPT Image 1 is an image generation model from OpenAI for visual creation workflows. It supports text and image inputs for generation, restyling, or edit-style workflows.
o4 Mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities.
GPT 4o Mini TTS (2025-03-20) is OpenAI's cost-efficient text-to-speech model. It converts text input into natural-sounding audio output, supporting a variety of voices and tones.
The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. It supports up to 200K of input context for long documents, codebases, and agent workflows.
Computer Use Preview is a multimodal model from OpenAI that can work across text and visual inputs. This entry tracks a preview release and capabilities may change before general availability.
GPT 4o Mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries. This entry tracks a preview release and capabilities may change before general availability.
GPT 4o Search Preview is trained to understand and execute web search queries. This entry tracks a preview release and capabilities may change before general availability.
GPT 4.5 Preview was OpenAI's research preview of GPT-4.5, a large general-purpose text and vision model that was deprecated in favor of GPT-4.1.
o3 mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. It supports up to 200K of input context for long documents, codebases, and agent workflows.
The December 17, 2024 snapshot of the GPT-4o Audio Preview family, supporting text and audio input and output through Chat Completions.
A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. This entry tracks a preview release and capabilities may change before general availability.
A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. This entry tracks a preview release and capabilities may change before general availability.
The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences.
o1 is designed to spend more time thinking before responding. It supports up to 200K of input context for long documents, codebases, and agent workflows.
Sora 1 is a video generation model from OpenAI for prompt-driven clip and scene creation. It is aimed at text-to-video, multimodal clip generation, and motion design workflows.
The October 1, 2024 snapshot of the GPT-4o Audio Preview family, supporting text and audio input and output through Chat Completions.
The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences.
o1 mini is OpenAI's smaller, cost-efficient speech-to-text model built on GPT-4o Mini audio capabilities. It is a smaller-footprint option suited to tighter latency or deployment budgets.
o1 preview is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. This entry tracks a preview release and capabilities may change before general availability.
The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability.
GPT 4o (2024-05-13) is an OpenAI model, released in May 2024, supporting both text and image inputs with text outputs. It accepts text and image inputs and produces text outputs.
GPT 4 Turbo is the production GPT-4 Turbo model with text and image input. The stable alias resolves to the April 9, 2024 snapshot.
The January 25, 2024 GPT-4 Turbo preview snapshot. The `gpt-4-turbo-preview` alias pointed to this snapshot before the production GPT-4 Turbo release.
The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while...
The November 6, 2023 vision-capable GPT-4 Turbo preview snapshot, served as `gpt-4-1106-vision-preview` and later superseded by GPT-4 Turbo.
GPT 3.5 Turbo Instruct is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.
The November 6, 2023 text-only GPT-4 Turbo preview snapshot, served by OpenAI as `gpt-4-1106-preview`.
Dall-E 3 is an image generation model from OpenAI for visual creation workflows. It is aimed at illustration, design exploration, and marketing creative.
GPT 3.5 Turbo (2023-11-06) is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.
Babbage 002 is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Davinci 002 is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
GPT 3.5 Turbo 0613 is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.
This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost.
GPT 4 (2023-06-13) is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning.
GPT 4 32K 0613 is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.
GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.
GPT 3.5 Turbo (2024-01-25) is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.
GPT 4 (2023-03-14) is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning.
GPT 4 32K is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.
GPT 4 32K 0314 is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.
Dall-E 2 is an image generation model from OpenAI for visual creation workflows. It is aimed at illustration, design exploration, and marketing creative.
Dall-E is an image generation model from OpenAI for visual creation workflows. It is aimed at illustration, design exploration, and marketing creative.
Ada is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Babbage is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Curie is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Davinci is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
GPT 2 is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.
GPT 1 is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.
Code Cushman 001 is a coding model from OpenAI for code generation, edits, and software tasks. It accepts text inputs and produces text outputs.
Code Cushman 002 is a coding model from OpenAI for code generation, edits, and software tasks. It accepts text inputs and produces text outputs.
Code Davinci 001 is a coding model from OpenAI for code generation, edits, and software tasks. It accepts text inputs and produces text outputs.
Code Davinci 002 is a coding model from OpenAI for code generation, edits, and software tasks. It accepts text inputs and produces text outputs.
Code Davinci Edit 001 is a coding model from OpenAI for code generation, edits, and software tasks. It accepts text inputs and produces text outputs.
Code Search Ada Code 001 is trained to understand and execute web search queries. It is aimed at retrieval-heavy assistants, browsing, and research synthesis.
Code Search Ada Text 001 is trained to understand and execute web search queries. It is aimed at retrieval-heavy assistants, browsing, and research synthesis.
Code Search Babbage Code 001 is trained to understand and execute web search queries. It is aimed at retrieval-heavy assistants, browsing, and research synthesis.
Code Search Babbage Text 001 is trained to understand and execute web search queries. It is aimed at retrieval-heavy assistants, browsing, and research synthesis.
Text Ada 001 is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Text Babbage 001 is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Text Curie 001 is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Text Davinci 001 is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Text Davinci 002 is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Text Davinci 003 is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Text Davinci Edit 001 is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Text Moderation 007 is a safety model from OpenAI for moderation, prompt filtering, and policy enforcement. It is suited to input filtering, safety checks, and policy enforcement in LLM applications.
Text Search Ada Doc 001 is trained to understand and execute web search queries. It is aimed at retrieval-heavy assistants, browsing, and research synthesis.
Text Search Ada Query 001 is trained to understand and execute web search queries. It is aimed at retrieval-heavy assistants, browsing, and research synthesis.
Text Search Babbage Doc 001 is trained to understand and execute web search queries. It is aimed at retrieval-heavy assistants, browsing, and research synthesis.
Text Search Babbage Query 001 is trained to understand and execute web search queries. It is aimed at retrieval-heavy assistants, browsing, and research synthesis.
Text Search Curie Doc 001 is trained to understand and execute web search queries. It is aimed at retrieval-heavy assistants, browsing, and research synthesis.
Text Search Curie Query 001 is trained to understand and execute web search queries. It is aimed at retrieval-heavy assistants, browsing, and research synthesis.
Text Search Davinci Doc 001 is trained to understand and execute web search queries. It is aimed at retrieval-heavy assistants, browsing, and research synthesis.
Text Search Davinci Query 001 is trained to understand and execute web search queries. It is aimed at retrieval-heavy assistants, browsing, and research synthesis.
Text Similarity Ada 001 is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Text Similarity Babbage 001 is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Text Similarity Curie 001 is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.
Text Similarity Davinci 001 is a language model from OpenAI for chat, writing, analysis, and general-purpose automation. It accepts text inputs and produces text outputs.