response - API Doc-CometAPI

Used to send a request to generate a chat completion message. The request should contain a model parameter, specifying the model to be used, and a list of inputs, containing roles and message content;

Request

Header Params

Authorization

string

required

Example:

Bearer {{api-key}}

Body Params application/json

model

string

required

Specifies the model used to generate the completion message.

Default:

o3-pro

input

array [object {2}]

required

Input parameters containing roles and message content

role

string

required

role

content

string

required

content

Example

{
    "model": "o3-pro",
    "input": [
        {
            "role": "user",
            "content": "say yes"
        }
    ]
}

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

Responses

🟢200Successful Response

application/json

Body

string

required

A unique identifier for this API request.

object

string

required

Returns the type of the object

created

integer

required

Unix timestamp of when the request processing completed

model

string

required

The specific model name used for this request.

system_fingerprint

string

required

System fingerprint, representing the backend configuration used for model execution.

choices

array [object {3}]

required

A list containing the model's generated results. If n > 1 was specified in the request, this may contain multiple result objects.

index

integer

optional

The index of this result in the list, starting from 0.

message

object

optional

The message content object generated by the model.

finish_reason

string

optional

The reason why the model stopped generating.

usage

object

required

Token usage statistics for this request.

completion_tokens

integer

required

The number of tokens consumed by the model's generated message (completion).

completion_tokens_details

object

required

Detailed information about completion_tokens

prompt_tokens

integer

required

The number of tokens consumed by the user's input prompt.

prompt_tokens_details

object

required

Detailed information about prompt_tokens

total_tokens

integer

required

The total number of tokens consumed by this request

Example

{
    "id": "chatcmpl-AreYSBEwmzB0kY3GxzBEhE1Olct83",
    "object": "chat.completion",
    "created": 1737350640,
    "model": "o3-pro",
    "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
    }
}