Skip to main content
POST
/
v1
/
responses
curl --request POST \
  --url https://api.foxapi.cc/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-5.4",
  "input": "Explain the design principles of RESTful APIs"
}
'
{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1757165031,
  "model": "<string>",
  "status": "completed",
  "output": [
    {
      "type": "message",
      "id": "msg_abc123",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Hello! How can I help you today?"
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 20,
    "output_tokens": 50,
    "total_tokens": 70
  }
}

Documentation Index

Fetch the complete documentation index at: https://docs.foxapi.cc/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

All APIs require Bearer Token authentication

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

application/json
​
model
string
required

Model name

Example:

"gpt-5.4"

​
input
required

Text input or message list for generating a response

​
stream
boolean
default:false

Whether to stream the response

​
temperature
number

Sampling temperature (0-2)

Required range: 0 <= x <= 2
​
max_output_tokens
integer

Maximum number of output tokens to generate

​
top_p
number

Nucleus sampling parameter (0-1)

Required range: 0 <= x <= 1
​
previous_response_id
string

ID of the previous response, used for multi-turn conversations

​
instructions
string

System-level instructions

​
tools
object[]

Available tools list

​
text
object

Text output format configuration

Response

Response API success

​
id
string

Unique response ID

Example:

"resp_abc123"

​
object
enum<string>

Object type

Available options:
response
​
created_at
integer

Creation timestamp

Example:

1757165031

​
model
string

Model used

​
status
enum<string>

The status of the response

Available options:
completed,
failed,
in_progress,
incomplete
Example:

"completed"

​
output
object[]

List of output items

​
usage
object

Token usage statistics