Chat（Reasoning mode）

POST

/chat/completions

Add inference ability to all models, just add the suffix -r1-fusion to the model name.
For example: gpt-4o-r1-fusion
Inspired by Deepclaude. The principle is to ask the user's questions first, obtain the thinking process, and then splice the thinking process and the problem together, and give it to the original model.
This is a multi-model fusion method that works on the 302 platform for any model
This feature can be used with image analysis or network search
For example: gpt-4o-r1-fusion-web-search
Price: + DeepSeek-R1-302 model cost based on the original model

Request

Header Params

Body Params application/json

Example

{
    "model": "gpt-4o-r1-fusion",
    "stream": false,
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "1+2+3+...+100=?"
                }
            ]
        }
    ]
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.302.ai/v1/chat/completions' \
--header 'Accept: application/json' \
--header 'Authorization: Bearer sk-jls4AaVBGoe1GwZD64qZA1qyKTN1MPHa4NmvH1cT68z7K1Zz' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "gpt-4o-r1-fusion",
    "stream": false,
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "1+2+3+...+100=?"
                }
            ]
        }
    ]
}'

Responses

🟢200OK

application/json

Body

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
    }
}

Modified at 2025-03-03 02:39:34

Chat（Image analysis）

Chat（Link Parsing）