gpt-3.5-turbo
and gpt-4
earlier this year, and in only a short few months, have seen incredible applications built by developers on top of these models.gpt-3.5-turbo
和 gpt-4
,在短短几个月内,已经看到开发人员在这些模型之上构建了令人难以置信的应用程序。gpt-4
and gpt-3.5-turbo
gpt-4
和 gpt-3.5-turbo
的更新和更易操纵的版本gpt-3.5-turbo
(vs the standard 4k version)gpt-3.5-turbo
的新 16k 上下文版本(与标准 4k 版本相比)gpt-3.5-turbo
gpt-3.5-turbo
的输入token成本降低 25%gpt-3.5-turbo-0301
and gpt-4-0314
modelsgpt-3.5-turbo-0301
和 gpt-4-0314
模型的弃用时间表gpt-4-0613
and gpt-3.5-turbo-0613
, and have the model intelligently choose to output a JSON object containing arguments to call those functions. This is a new way to more reliably connect GPT's capabilities with external tools and APIs.gpt-4-0613
和 gpt-3.5-turbo-0613
描述函数,并让模型智能地选择输出包含调用这些函数的参数的 JSON 对象。这是一种更可靠地将 GPT 功能与外部工具和 API 连接的新方法。send_email(to: string, body: string)
, or “What’s the weather like in Boston?” to get_current_weather(location: string, unit: 'celsius' | 'fahrenheit')
.send_email(to: string, body: string)
之类的函数调用,或者“波士顿的天气怎么样?”到 get_current_weather(location: string, unit: 'celsius' | 'fahrenheit')
。get_customers_by_revenue(start_date: string, end_date: string, limit: int)
, or “How many orders did Acme, Inc. place last month?” to a SQL query using sql_query(query: string)
.get_customers_by_revenue(start_date: string, end_date: string, limit: int)
,或“Acme, Inc. 上个月下了多少订单?”到使用 sql_query(query: string)
的SQL 查询。extract_people_data(people: [{name: string, birthday: string, location: string}])
, to extract all people mentioned in a Wikipedia article.extract_people_data(people: [{name: string, birthday: string, location: string}])
的函数,以提取维基百科文章中提到的所有人。/v1/chat/completions
endpoint, functions
and function_call
, that allow developers to describe functions to the model via JSON Schema, and optionally ask it to call a specific function. Get started with our developer documentation and add evals if you find cases where function calling could be improved/v1/chat/completions
端点、 functions
和 function_call
中的新 API 参数启用,允许开发人员通过 JSON 模式向模型描述函数,并可选择要求它调用特定函数。开始使用我们的开发人员文档,如果您发现可以改进函数调用的情况,请添加评估。Function calling example 函数调用示例
请阅读原文查看。
gpt-4-0613
includes an updated and improved model with function calling.gpt-4-0613
包括一个更新和改进的模型,带有函数调用。gpt-4-32k-0613
includes the same improvements as gpt-4-0613
, along with an extended context length for better comprehension of larger texts.gpt-4-32k-0613
包括与 gpt-4-0613
相同的改进,以及扩展的上下文长度,以便更好地理解更大的文本。gpt-3.5-turbo-0613
includes the same function calling as GPT-4 as well as more reliable steerability via the system message, two features that allow developers to guide the model's responses more effectively.gpt-3.5-turbo-0613
包括与 GPT-4 相同的函数调用以及通过系统消息提供的更可靠的可操纵性,这两个功能允许开发人员更有效地指导模型的响应。gpt-3.5-turbo-16k
offers 4 times the context length of gpt-3.5-turbo
at twice the price: $0.003 per 1K input tokens and $0.004 per 1K output tokens. 16k context means the model can now support ~20 pages of text in a single request.gpt-3.5-turbo-16k
以两倍的价格提供 gpt-3.5-turbo
的上下文长度的 4 倍:每 1K 输入令牌 0.003 美元,每 1K 输出令牌 0.004 美元。 16k 上下文意味着该模型现在可以在单个请求中支持约 20 页文本。gpt-4
and gpt-3.5-turbo
that we announced in March. Applications using the stable model names (gpt-3.5-turbo
, gpt-4
, and gpt-4-32k
) will automatically be upgraded to the new models listed above on June 27th. For comparing model performance between versions, our Evals library supports public and private evals to show how model changes will impact your use cases. gpt-4
和 gpt-3.5-turbo
初始版本进行升级和弃用。使用稳定模型名称( gpt-3.5-turbo
、 gpt-4
和 gpt-4-32k
)的应用程序将在 6 月 27 日自动升级到上面列出的新模型。为了比较版本之间的模型性能,我们的 Evals 库支持公共和私有评估,以显示模型更改将如何影响您的用例。gpt-3.5-turbo-0301
, gpt-4-0314
, or gpt-4-32k-0314
in the ‘model’ parameter of their API request. These older models will be accessible through September 13th, after which requests specifying those model names will fail. You can stay up to date on model deprecations via our model deprecation page. This is the first update to these models; so, we eagerly welcome developer feedback to help us ensure a smooth transition.gpt-3.5-turbo-0301
、 gpt-4-0314
或 gpt-4-32k-0314
来继续使用旧模型。这些旧模型将在 9 月 13 日之前开放,之后指定这些模型名称的请求将失败。您可以通过我们的模型弃用页面了解模型弃用的最新信息。这是这些模型的第一次更新;因此,我们热切欢迎开发人员提供反馈,以帮助我们确保顺利过渡。text-embedding-ada-002
is our most popular embeddings model. Today we’re reducing the cost by 75% to $0.0001 per 1K tokens.text-embedding-ada-002
是我们最受欢迎的嵌入模型。今天,我们将成本降低 75% 至每 1K 代币 0.0001 美元。gpt-3.5-turbo
is our most popular chat model and powers ChatGPT for millions of users. Today we're reducing the cost of gpt-3.5-turbo’s
input tokens by 25%. Developers can now use this model for just $0.0015 per 1K input tokens and $0.002 per 1K output tokens, which equates to roughly 700 pages per dollar.gpt-3.5-turbo
是我们最受欢迎的聊天模型,为数百万用户提供 ChatGPT 支持。今天,我们将 gpt-3.5-turbo’s
输入代币的成本降低了 25%。开发人员现在可以以每 1K 输入令牌 0.0015 美元和每 1K 输出令牌 0.002 美元的价格使用该模型,这相当于每美元大约 700 页。gpt-3.5-turbo-16k
will be priced at $0.003 per 1K input tokens and $0.004 per 1K output tokens.gpt-3.5-turbo-16k
的定价为每 1K 输入代币 0.003 美元,每 1K 输出代币 0.004 美元。