Chat (o1 Series Model)

POST

/chat/completions

Support the model below：
o1
o1-mini
o1-preview
Note that this model does not support stream mode, nor does it support setting parameters like temperature, top_p, n, presence_penalty, or frequency_penalty. We have made it compatible on the server side, but passing these parameters will be invalid.

Token calculation method：
Input：prompt_tokens
Output：completion_tokens+reasoning_tokens

OpenAI Guide
OpenAI API Reference

Chat models take a series of messages as input and return a model-generated message as output. While the chat format is designed to make multi-turn conversations easy, it's just as useful for single-turn tasks without any conversation.

Price List：https://302.ai/pricing_api/

Request

Header Params

Body Params application/json

Example

{
  "model": "o1-mini",
  "stream": false,
  "messages": [
    {
      "role": "user",
      "content": "hello"
    }
  ]
}

Request 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": "o1-mini",
  "stream": false,
  "messages": [
    {
      "role": "user",
      "content": "hello"
    }
  ]
}'

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 2024-12-19 02:42:21

Chat (chatgpt-4o-latest)

Chat (o3 Series Model)