Models 模型

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.
OpenAI API 由一组具有不同功能和价格的多样化模型提供支持。您还可以通过微调对我们的模型进行自定义，以满足您的特定用例。

gpt-4o, 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).
gpt-4o 、 gpt-4-turbo 、 gpt-4 和 gpt-3.5-turbo 指向各自的最新型号版本。您可以通过查看发送请求后的响应对象来验证这一点。响应将包括所使用的具体型号版本（例如 gpt-3.5-turbo-1106 ）。

We also offer pinned model versions that developers can continue using for at least three months after an updated model has been introduced. With the new cadence of model updates, we are also giving people the ability to contribute evals to help us improve the model for different use cases. If you are interested, check out the OpenAI Evals repository.
我们还提供固定模型版本，开发者在更新模型推出后至少三个月内可以继续使用。随着新模型更新节奏的推出，我们还让人们能够贡献评估，以帮助我们改进模型以适应不同的使用场景。如果你感兴趣，请查看 OpenAI Evals 仓库。

Learn more about model deprecation on our deprecation page.
了解更多关于模型弃用的信息，请访问我们的弃用页面。

GPT-4o (“o” for “omni”) is our most advanced 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（“o”代表“omni”）是我们最先进的模型。它是多模态的（接受文本或图像输入并输出文本），具有与 GPT-4 Turbo 相同的高智能，但效率更高——生成文本的速度快 2 倍，成本降低 50%。此外，GPT-4o 在非英语语言的视觉和性能方面是我们所有模型中最好的。GPT-4o 在 OpenAI API 中向付费客户提供。了解如何在我们的文本生成指南中使用 GPT-4o。

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.
GPT-4 是一个大型多模态模型（接受文本或图像输入并输出文本），由于其更广泛的通用知识和高级推理能力，它能够比我们之前的任何模型更准确地解决困难问题。GPT-4 在 OpenAI API 中向付费客户提供。与 gpt-3.5-turbo 类似，GPT-4 针对聊天进行了优化，但在使用 Chat Completions API 进行传统完成任务时也能很好地工作。请参阅我们的文本生成指南，了解如何使用 GPT-4。

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.
对于许多基本任务，GPT-4 和 GPT-3.5 模型之间的差异并不显著。然而，在更复杂的推理情况下，GPT-4 比我们之前的任何模型都要强大得多。

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-4 在性能上超过了之前的大型语言模型，并且截至 2023 年，超过了大多数最先进的系统（这些系统通常具有特定基准的训练或手工工程）。在 MMLU 基准测试中，这是一套涵盖 57 个科目的英语多项选择题，GPT-4 不仅在英语方面大幅超越现有模型，还在其他语言中表现出色。

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.
GPT-3.5 Turbo 模型可以理解和生成自然语言或代码，并已通过聊天完成 API 进行了优化，但也适用于非聊天任务。

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 是一个可以根据自然语言描述创建逼真图像和艺术作品的人工智能系统。DALL·E 3 目前支持根据提示创建具有特定大小的新图像的功能。DALL·E 2 还支持编辑现有图像或创建用户提供图像的变体的功能。

DALL·E 3 is available through our Images API along with DALL·E 2. You can try DALL·E 3 through ChatGPT Plus.
DALL·E 3 可通过我们的图像 API 与 DALL·E 2 一起使用。您可以通过 ChatGPT Plus 试用 DALL·E 3。

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.
TTS 是一种将文本转换为自然语音的 AI 模型。我们提供两种不同的模型变体， tts-1 优化用于实时文本转语音的使用场景， tts-1-hd 优化用于质量。这些模型可以与音频 API 中的语音端点一起使用。

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.
Whisper 是一个通用的语音识别模型。它在一个多样化的音频大数据集上进行训练，同时也是一个多任务模型，能够执行多语言语音识别、语音翻译和语言识别。Whisper v2-large 模型目前可以通过我们的 API 使用，模型名称为 whisper-1 。

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.
目前，开源版本的 Whisper 与通过我们的 API 提供的版本之间没有区别。然而，通过我们的 API，我们提供了一个优化的推理过程，使得通过我们的 API 运行 Whisper 比通过其他方式运行要快得多。有关 Whisper 的更多技术细节，您可以阅读论文。

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.
嵌入是文本的数值表示，可用于衡量两段文本之间的相关性。嵌入对于搜索、聚类、推荐、异常检测和分类任务非常有用。您可以在公告博客文章中阅读更多关于我们最新嵌入模型的信息。

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 the following categories: hate, hate/threatening, self-harm, sexual, sexual/minors, violence, and violence/graphic. You can find out more in our moderation guide.
Moderation 模型旨在检查内容是否符合 OpenAI 的使用政策。模型提供分类功能，查找以下类别的内容：仇恨、仇恨/威胁、自残、色情、色情/未成年人、暴力和暴力/血腥。您可以在我们的审核指南中了解更多信息。

Moderation models take in an arbitrary sized input that is automatically broken up into chunks of 4,096 tokens. In cases where the input is more than 32,768 tokens, truncation is used which in a rare condition may omit a small number of tokens from the moderation check.
Moderation models 接受任意大小的输入，自动分成 4,096 个标记的块。在输入超过 32,768 个标记的情况下，使用截断，这在极少数情况下可能会从审核检查中省略少量标记。

The final results from each request to the moderation endpoint shows the maximum value on a per category basis. For example, if one chunk of 4K tokens had a category score of 0.9901 and the other had a score of 0.1901, the results would show 0.9901 in the API response since it is higher.
每次请求审核端点的最终结果显示每个类别的最大值。例如，如果一个 4K 令牌块的类别得分为 0.9901，而另一个块的得分为 0.1901，则结果将在 API 响应中显示 0.9901，因为它更高。

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.
GPT 基础模型可以理解和生成自然语言或代码，但未经过指令跟随训练。这些模型是为了替代我们原始的 GPT-3 基础模型，并使用传统的 Completions API。大多数客户应使用 GPT-3.5 或 GPT-4。

Your data is your data.
您的数据是您的数据。

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). One advantage to opting in is that the models may get better at your use case over time.
截至 2023 年 3 月 1 日，发送到 OpenAI API 的数据将不会用于训练或改进 OpenAI 模型（除非您明确选择加入）。选择加入的一个好处是，模型可能会随着时间的推移在您的使用案例中变得更好。

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.
为了帮助识别滥用行为，API 数据可能会保留长达 30 天，之后将被删除（除非法律另有要求）。对于具有敏感应用的可信客户，可能提供零数据保留。采用零数据保留时，请求和响应主体不会持久化到任何日志机制中，只存在于内存中以处理请求。

Note that this data policy does not apply to OpenAI's non-API consumer services like ChatGPT or DALL·E Labs.
请注意，此数据政策不适用于 OpenAI 的非 API 消费者服务，如 ChatGPT 或 DALL·E Labs。

* Image inputs via the gpt-4-turbo model (or previously gpt-4-vision-preview) are not eligible for zero retention.
* 通过 gpt-4-turbo 模型（或之前的 gpt-4-vision-preview ）输入的图像不符合零保留的条件。

** 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.
与助理 API 相关的对象在您通过 API 或仪表板删除它们后 30 天内从我们的服务器中删除。未通过 API 或仪表板删除的对象将无限期保留。

For details, see our API data usage policies. To learn more about zero retention, get in touch with our sales team.
有关详细信息，请参阅我们的 API 数据使用政策。要了解更多关于零保留的信息，请与我们的销售团队联系。