Create chat completion

POST

/v1/chat/completions

原文参考：https://platform.openai.com/docs/api-reference/chat/create

请求参数

Authorization

在 Header 添加参数

Authorization

，其值为在 Bearer 之后拼接 Token

示例：

Authorization: Bearer ********************

Body 参数application/json

messages

array [object {3}]

必需

A list of messages comprising the conversation so far. Example Python code.

role

string

必需

The role of the messages author, in this case system./assistant/user

content

string

必需

The contents of the system/assistant/user message.

name

string

可选

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

model

string

必需

ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.

frequency_penalty

number

可选

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

默认值:

logit_bias

object

可选

Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

logprobs

boolean

可选

Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message. This option is currently not available on the gpt-4-vision-preview model.

默认值:

false

top_logprobs

integer

可选

An integer between 0 and 5 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.

max_tokens

integer

可选

The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. Example Python code for counting tokens.

integer

可选

How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

默认值:

presence_penalty

number

可选

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

默认值:

response_format

object

可选

An object specifying the format that the model must output. Compatible with GPT-4 Turbo and all GPT-3.5 Turbo models newer than gpt-3.5-turbo-1106.

seed

integer

可选

This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

stop

object

可选

Up to 4 sequences where the API will stop generating further tokens.

stream

boolean

可选

If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code.

默认值:

false

temperature

number

可选

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

默认值:

top_p

number

可选

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

默认值:

tools

array [object {2}]

可选

A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for.

type

string

必需

The type of the tool. Currently, only function is supported.

function

object

必需

tool_choice

object

可选

Controls which (if any) function is called by the model. none means the model will not call a function and instead generates a message. auto means the model can pick between generating a message or calling a function. Specifying a particular function via {"type": "function", "function": {"name": "my_function"}} forces the model to call that function. none is the default when no functions are present. auto is the default if functions are present.

user

string

可选

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

function_call

object

可选

Deprecated in favor of tool_choice.

functions

array[string]

可选

Deprecated in favor of tools.

示例

{
  "model": "claude-3-7-sonnet-20250219",
  "stream": true,
  "stream_options": {
    "include_usage": true
  },
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "你好！"
    }
  ]
}

示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.aigateway.work/v1/chat/completions' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "claude-3-7-sonnet-20250219",
  "stream": true,
  "stream_options": {
    "include_usage": true
  },
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "你好！"
    }
  ]
}'

返回响应

🟢200成功

application/json

Body

string

必需

A unique identifier for the chat completion.

object

string

必需

The object type, which is always chat.completion.

created

integer

必需

The Unix timestamp (in seconds) of when the chat completion was created.

model

string

必需

The model used for the chat completion.

choices

array [object {4}]

必需

A list of chat completion choices. Can be more than one if n is greater than 1.

index

integer

可选

The index of the choice in the list of choices.

message

object

可选

A chat completion message generated by the model.

logprobs

null

可选

Log probability information for the choice.

finish_reason

string

可选

The reason the model stopped generating tokens. This will be stop if the model hit a natural stop point or a provided stop sequence, length if the maximum number of tokens specified in the request was reached, content_filter if content was omitted due to a flag from our content filters, tool_calls if the model called a tool, or function_call (deprecated) if the model called a function.

usage

object

可选

Usage statistics for the completion request.

prompt_tokens

integer

必需

Number of tokens in the prompt.

completion_tokens

integer

必需

Number of tokens in the generated completion.

total_tokens

integer

必需

Total number of tokens used in the request (prompt + completion).

system_fingerprint

string

可选

This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.

示例

{
  "id": "chatcmpl-8uxQ3O1u0Z79h7u9JjZ4FOEZapsko",
  "object": "chat.completion",
  "created": 1708585467,
  "model": "gpt-3.5-turbo-0125",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "你好！有什么我可以帮助你的吗？"
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 18,
    "total_tokens": 38
  },
  "system_fingerprint": "fp_cbdb91ce3f"
}

修改于 2025-06-30 03:20:35

ReActor image

Create chat completion with stream