Models

The OpenAI API is powered by a diverse set of models with different capabilities and price points. You can also make customizations to our models for your specific use case with fine-tuning.

gpt-4o, gpt-4o-mini, gpt-4-turbo, gpt-4, and gpt-3.5-turbo point to their respective latest model version. You can verify this by looking at the response object after sending a request. The response will include the specific model version used (e.g. gpt-3.5-turbo-1106). The chatgpt-4o-latest model version continuously points to the version of GPT-4o used in ChatGPT, and is updated frequently, when there are significant changes. With the exception of chatgpt-4o-latest, we offer pinned model versions that developers can continue using for at least three months after an updated model has been introduced.

Learn more about model deprecation on our deprecation page.

GPT-4o (“o” for “omni”) is our most advanced GPT model. It is multimodal (accepting text or image inputs and outputting text), and it has the same high intelligence as GPT-4 Turbo but is much more efficient—it generates text 2x faster and is 50% cheaper. Additionally, GPT-4o has the best vision and performance across non-English languages of any of our models. GPT-4o is available in the OpenAI API to paying customers. Learn how to use GPT-4o in our text generation guide.

GPT-4o mini (“o” for “omni”) is our most advanced model in the small models category, and our cheapest model yet. It is multimodal (accepting text or image inputs and outputting text), has higher intelligence than gpt-3.5-turbo but is just as fast. It is meant to be used for smaller tasks, including vision tasks.

We recommend choosing gpt-4o-mini where you would have previously used gpt-3.5-turbo as this model is more capable and cheaper.

This is a preview release of the GPT-4o Realtime and Audio models. The gpt-4o-realtime-* models are capable of responding to audio and text inputs over a WebSocket interface. Learn more in the Realtime API guide. The gpt-4o-audio-* models below can be used in Chat Completions to generate audio responses.

The o1 series of large language models are trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user.
Learn about the capabilities and limitations of o1 models in our reasoning guide.

There are two model types available today:

• o1-preview: reasoning model designed to solve hard problems across domains.
• o1-mini: faster and cheaper reasoning model particularly good at coding, math, and science.

GPT-4 is a large multimodal model (accepting text or image inputs and outputting text) that can solve difficult problems with greater accuracy than any of our previous models, thanks to its broader general knowledge and advanced reasoning capabilities. GPT-4 is available in the OpenAI API to paying customers. Like gpt-3.5-turbo, GPT-4 is optimized for chat but works well for traditional completions tasks using the Chat Completions API. Learn how to use GPT-4 in our text generation guide.

For many basic tasks, the difference between GPT-4 and GPT-3.5 models is not significant. However, in more complex reasoning situations, GPT-4 is much more capable than any of our previous models.

GPT-4 outperforms both previous large language models and as of 2023, most state-of-the-art systems (which often have benchmark-specific training or hand-engineering). On the MMLU benchmark, an English-language suite of multiple-choice questions covering 57 subjects, GPT-4 not only outperforms existing models by a considerable margin in English, but also demonstrates strong performance in other languages.

GPT-3.5 Turbo models can understand and generate natural language or code and have been optimized for chat using the Chat Completions API but work well for non-chat tasks as well.

DALL·E is a AI system that can create realistic images and art from a description in natural language. DALL·E 3 currently supports the ability, given a prompt, to create a new image with a specific size. DALL·E 2 also support the ability to edit an existing image, or create variations of a user provided image.

DALL·E 3 is available through our Images API along with DALL·E 2. You can try DALL·E 3 through ChatGPT Plus.

TTS is an AI model that converts text to natural sounding spoken text. We offer two different model variates, tts-1 is optimized for real time text to speech use cases and tts-1-hd is optimized for quality. These models can be used with the Speech endpoint in the Audio API.

Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification. The Whisper v2-large model is currently available through our API with the whisper-1 model name.

Currently, there is no difference between the open source version of Whisper and the version available through our API. However, through our API, we offer an optimized inference process which makes running Whisper through our API much faster than doing it through other means. For more technical details on Whisper, you can read the paper.

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. You can read more about our latest embedding models in the announcement blog post.

---

The Moderation models are designed to check whether content complies with OpenAI's usage policies. The models provide classification capabilities that look for content in categories like hate, self-harm, sexual content, violence, and others. Learn more about moderating text and images in our moderation guide.

GPT base models can understand and generate natural language or code but are not trained with instruction following. These models are made to be replacements for our original GPT-3 base models and use the legacy Completions API. Most customers should use GPT-3.5 or GPT-4.

Your data is your data.

As of March 1, 2023, data sent to the OpenAI API will not be used to train or improve OpenAI models (unless you explicitly opt-in to share data with us, such as by providing feedback in the Playground). One advantage to opting in is that the models may get better at your use case over time.

To help identify abuse, API data may be retained for up to 30 days, after which it will be deleted (unless otherwise required by law). For trusted customers with sensitive applications, zero data retention may be available. With zero data retention, request and response bodies are not persisted to any logging mechanism and exist only in memory in order to serve the request.

Note that this data policy does not apply to OpenAI's non-API consumer services like ChatGPT or DALL·E Labs.

Endpoint	Data used for training	Default retention	Eligible for zero retention
/v1/chat/completions*	No	30 days	Yes, except (a) image inputs, (b) schemas provided for Structured Outputs, or (c) audio outputs. *
/v1/assistants	No	30 days **	No
/v1/threads	No	30 days **	No
/v1/threads/messages	No	30 days **	No
/v1/threads/runs	No	30 days **	No
/v1/vector_stores	No	30 days **	No
/v1/threads/runs/steps	No	30 days **	No
/v1/images/generations	No	30 days	No
/v1/images/edits	No	30 days	No
/v1/images/variations	No	30 days	No
/v1/embeddings	No	30 days	Yes
/v1/audio/transcriptions	No	Zero data retention	-
/v1/audio/translations	No	Zero data retention	-
/v1/audio/speech	No	30 days	Yes
/v1/files	No	Until deleted by customer	No
/v1/fine_tuning/jobs	No	Until deleted by customer	No
/v1/batches	No	Until deleted by customer	No
/v1/moderations	No	Zero data retention	-
/v1/completions	No	30 days	Yes
/v1/realtime (beta)	No	30 days	Yes

* Chat Completions:

• Image inputs via the gpt-4o, gpt-4o-mini, chatgpt-4o-latest, or gpt-4-turbo models (or previously gpt-4-vision-preview) are not eligible for zero retention.
• Audio outputs are stored for 1 hour to enable multi-turn conversations, and are not currently eligible for zero retention.
• When Structured Outputs is enabled, schemas provided (either as the response_format or in the function definition) are not eligible for zero retention, though the completions themselves are.
• When using Stored Completions via the store: true option in the API, those completions are stored for 30 days. Completions are stored in an unfiltered form after an API response, so please avoid storing completions that contain sensitive data.

** Assistants API:

• Objects related to the Assistants API are deleted from our servers 30 days after you delete them via the API or the dashboard. Objects that are not deleted via the API or dashboard are retained indefinitely.

Evaluations:

• Evaluation data: When you create an evaluation, the data related to that evaluation is deleted from our servers 30 days after you delete it via the dashboard. Evaluation data that is not deleted via the dashboard is retained indefinitely.

For details, see our API data usage policies. To learn more about zero retention, get in touch with our sales team.