Chat

The endpoint POST https://api.cometapi.com/v1/chat/completions is used to send a request to generate chat completions. The request should include a model parameter specifying the model to use, a list of messages containing the role and content of the messages, and a stream parameter to indicate whether to stream the response.

Request Body

model (string): Specifies the model to use for generating completions.

messages (array): Contains the role and content of the messages for which completions are to be generated.

role (string): Specifies the role of the message (e.g., "user", "assistant", "system").

content (string): The content of the message for which completions are to be generated.

stream (boolean): Indicates whether to stream the response.

Request

Header Params

Authorization

string

required

Example:

Bearer {{api-key}}

Body Params application/json

model

string

required

messages

array [object {2}]

required

role

string

optional

content

string

optional

stream

boolean

required

Example

{
  "model": "gpt-4o",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false
}

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

Responses

🟢200Successful Response

text/plain

Body

string

required

object

string

required

created

integer

required

model

string

required

system_fingerprint

string

required

choices

array [object {3}]

required

index

integer

optional

message

object

optional

finish_reason

string

optional

usage

object

required

completion_tokens

integer

required

completion_tokens_details

object

required

prompt_tokens

integer

required

prompt_tokens_details

object

required

total_tokens

integer

required

Example

{
  "id": "chatcmpl-AreYSBEwmzB0kY3GxzBEhE1Olct83",
  "object": "chat.completion",
  "created": 1737350640,
  "model": "gpt-4o-2024-08-06",
  "system_fingerprint": "fp_f3927aa00d",
  "choices": [
    {
      "index": 0,
      "message": {
        "content": "Hello! How can I assist you today?",
        "role": "assistant"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "completion_tokens": 9,
    "completion_tokens_details": {},
    "prompt_tokens": 9,
    "prompt_tokens_details": {},
    "total_tokens": 18
  }
}

Request Body#

Request

Request samples

Responses

Request Body