Chat (UniFuncs Deep Research) - 302.AI API Document

Request

Query Params

async

string

optional

Example:

true

Header Params

Content-Type

string

required

Example:

application/json

Accept

string

required

Example:

application/json

Authorization

string

optional

Example:

Bearer {{YOUR_API_KEY}}

Body Params application/json

model

string

required

The ID of the model to use. For details on which models are compatible with the chat API, see the model endpoint compatibility table.

messages

array [object {2}]

required

Generate chat completion messages in chat format.

role

string

optional

content

string

optional

stream

boolean

required

If set, partial message increments will be sent, just like in ChatGPT. When tokens become available, they will be sent as plain data server-sent events with data: [DONE], and the stream will be terminated by the message. For example code, see the OpenAI Cookbook.

introduction

string

optional

Set the role and tone of a researcher

plan_approval

boolean

optional

Before conducting the research, generate a research plan and wait for the user to approve or modify it.

max_depth

integer

optional

The maximum research depth. It is recommended to set it to 25 rounds for optimal results.

output_type

string

optional

Expected output style type, default is report
report (Ten-thousand-word report)
summary (Concise summary)
wechat-article (WeChat official account article)
xiaohongshu-article (Xiaohongshu article)
toutiao-article (Toutiao article)
zhihu-article (Zhihu article)
zhihu-answer (Zhihu answer)
weibo-article (Weibo post)

output_length

integer

optional

Expected output content length (the model may not necessarily comply): 1000-30000

reference_style

string

optional

Specify the output format for citations. The default is link.

content_verification

boolean

optional

Whether to enable the content verification feature, significantly improving the accuracy of the final report

Example

{
  "model": "unifuncs-deepresearch",
  "messages": [
    {
      "role": "user",
      "content": "调研ANP协议"
    }
  ],
  "stream": true,
  "introduction": "您是 U深研，一个由 UniFuncs 自主研发的专注于网络信息深度研究（Deep Research）的专家。",
  "plan_approval": false,
  "max_depth": 25,
  "output_type": "report",
  "output_length": 10000,
  "reference_style": "link",
  "content_verification": false
}

Request samples

Shell

JavaScript

Java

Swift

Go

PHP

Python

HTTP

C

C#

Objective-C

Ruby

OCaml

Dart

R

curl --location --request POST 'https://api.302.ai/v1/chat/completions?async=true' \
--header 'Accept: application/json' \
--header 'Authorization: Bearer sk-jls4AaVBGoe1GwZD64qZA1qyKTN1MPHa4NmvH1cT68z7K1Zz' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "unifuncs-deepresearch",
  "messages": [
    {
      "role": "user",
      "content": "调研ANP协议"
    }
  ],
  "stream": true,
  "introduction": "您是 U深研，一个由 UniFuncs 自主研发的专注于网络信息深度研究（Deep Research）的专家。",
  "plan_approval": false,
  "max_depth": 25,
  "output_type": "report",
  "output_length": 10000,
  "reference_style": "link",
  "content_verification": false
}'

Responses

🟢200OK

application/json

Body

id

string

required

object

string

required

created

integer

required

choices

array [object {3}]

required

index

integer

optional

message

object

optional

finish_reason

string

optional

usage

object

required

prompt_tokens

integer

required

completion_tokens

integer

required

total_tokens

integer

required

Example

{
    "id": "chatcmpl-123",
    "object": "chat.completion",
    "created": 1677652288,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "\n\nHello there, how may I assist you today?"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 9,
        "completion_tokens": 12,
        "total_tokens": 21
    }
}