模型说明
概述
OpenAI API由一系列具有不同功能和价格点的多样化模型驱动。您还可以通过微调对我们的原始基础模型进行有限的定制，以适应您特定的使用情况。
| Model | Description |
|---|---|
| GPT-4 Limited beta | A set of models that improve on GPT-3.5 and can understand as well as generate natural language or code |
| GPT-3.5 | A set of models that improve on GPT-3 and can understand as well as generate natural language or code |
| DALL·EBeta | A model that can generate and edit images given a natural language prompt |
| WhisperBeta | A model that can convert audio into text |
| Embeddings | A set of models that can convert text into a numerical form |
| Moderation | A fine-tuned model that can detect whether text may be sensitive or unsafe |
| GPT-3 | A set of models that can understand and generate natural language |
| Deprecated | A full list of models that have been deprecated |
持续模型升级
随着gpt-3.5-turbo的发布，我们的一些模型现在正在持续更新。我们还提供静态模型版本，开发人员可以在更新的模型推出后至少三个月内继续使用。随着模型更新的新节奏，我们还允许人们贡献评估数据，以帮助我们改进适用于不同用例的模型。如果您有兴趣，请查看OpenAI Evals存储库。
以下模型是临时快照，一旦更新版本可用，我们将宣布它们的弃用日期。如果您想使用最新的模型版本，请使用标准的模型名称，如gpt-4或gpt-3.5-turbo。
| Model Name | Discontinuation Date | Replacement Model |
|---|---|---|
| gpt-3.5-turbo-0301 | 09/13/2023 | gpt-3.5-turbo-0613 |
| gpt-4-0314 | 09/13/2023 | gpt-4-0613 |
| gpt-4-32k-0314 | 09/13/2023 | gpt-4-32k-0613 |
GPT-4 Limited beta
INFO
目前，GPT-4处于有限的测试版（beta）阶段，只对那些被授权的用户开放。请加入等待列表以获取访问权限。
GPT-4是一个大型多模态模型（目前接受文本输入并生成文本输出，未来将支持图像输入），它能够比我们以前的任何模型更准确地解决困难的问题，这要归功于它更广泛的通用知识和先进的推理能力。与gpt-3.5-turbo一样，GPT-4经过优化以进行聊天，并且在传统的文本补全任务中也能很好地工作，可以使用Chat Completions API来实现。在我们的GPT指南中了解如何使用GPT-4。
INFO
2023 年 6 月 27 日，gpt-4 将从 gpt-4-0314 更新为最新模型迭代 gpt-4-0613。
| Latest Model | Description | Max Tokens | Training Data |
|---|---|---|---|
| gpt-4 | More capable than any GPT-3.5 model, able to do more complex tasks, and optimized for chat. Will be updated with our latest model iteration 2 weeks after it is released. | 8,192 | Up to Sep 2021 |
| gpt-4-0613 | Snapshot of gpt-4 from June 13th 2023 with function calling data. Unlike gpt-4, this model will not receive updates, and will be deprecated 3 months after a new version is released. | 8,192 | Up to Sep 2021 |
| gpt-4-32k | Same capabilities as the base gpt-4 mode but with 4x the context length. Will be updated with our latest model iteration. | 32,768 | Up to Sep 2021 |
| gpt-4-32k-0613 | Snapshot of gpt-4-32 from June 13th 2023. Unlike gpt-4-32k, this model will not receive updates, and will be deprecated 3 months after a new version is released. | 32,768 | Up to Sep 2021 |
对于许多基本任务，GPT-4 和 GPT-3.5 模型之间的差异并不显着。 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更有能力。
GPT-3.5
GPT-3.5模型可以理解并生成自然语言或代码。 我们 GPT-3.5 系列中功能最强大且最具成本效益的模型是 gpt-3.5-turbo，它已针对聊天进行了优化，但也适用于传统的完成任务。
INFO
On June 27th, 2023, gpt-3.5-turbo will be updated to point from gpt-3.5-turbo-0301 to gpt-3.5-turbo-0613.
| Latest Model | Description | Max Tokens | Training Data |
|---|---|---|---|
| gpt-3.5-turbo | Most capable GPT-3.5 model and optimized for chat at 1/10th the cost of text-davinci-003. Will be updated with our latest model iteration 2 weeks after it is released. | 4,096 | Up to Sep 2021 |
| gpt-3.5-turbo-16k | Same capabilities as the standard gpt-3.5-turbo model but with 4 times the context. | 16,384 | Up to Sep 2021 |
| gpt-3.5-turbo-0613 | Snapshot of gpt-3.5-turbo from June 13th 2023 with function calling data. Unlike gpt-3.5-turbo, this model will not receive updates, and will be deprecated 3 months after a new version is released. | 4,096 | Up to Sep 2021 |
| gpt-3.5-turbo-16k-0613 | Snapshot of gpt-3.5-turbo-16k from June 13th 2023. Unlike gpt-3.5-turbo-16k, this model will not receive updates, and will be deprecated 3 months after a new version is released. | 16,384 | Up to Sep 2021 |
| text-davinci-003 | Can do any language task with better quality, longer output, and consistent instruction-following than the curie, babbage, or ada models. Also supports some additional features such as inserting text. | 4,097 | Up to Jun 2021 |
| text-davinci-002 | Similar capabilities to text-davinci-003 but trained with supervised fine-tuning instead of reinforcement learning | 4,097 | Up to Jun 2021 |
| code-davinci-002 | Optimized for code-completion tasks | 8,001 | Up to Jun 2021 |
INFO
我们建议使用 gpt-3.5-turbo 而不是其他 GPT-3.5 型号，因为它的成本更低，性能更高。
How we use your data
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 explitly opt in). 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.
模型端点兼容性
| Endpoint | Model Name |
|---|---|
| /v1/chat/completions | gpt-4, gpt-4-0613, gpt-4-32k, gpt-4-32k-0613, gpt-3.5-turbo, gpt-3.5-turbo-0613, gpt-3.5-turbo-16k, gpt-3.5-turbo-16k-0613 |
| /v1/completions | text-davinci-003, text-davinci-002, text-curie-001, text-babbage-001, text-ada-001 |
| /v1/edits | text-davinci-edit-001, code-davinci-edit-001 |
| /v1/audio/transcriptions | whisper-1 |
| /v1/audio/translations | whisper-1 |
| /v1/fine-tunes | davinci, curie, babbage, ada |
| /v1/embeddings | text-embedding-ada-002, text-search-ada-doc-001 |
| /v1/moderations | text-moderation-stable, text-moderation-latest |
This list does not include our first-generation embedding models nor our DALL·E models. 此列表不包括我们的第一代嵌入模型和DALL·E模型。