Passer au contenu principal
POST
/
v1
/
responses
curl --request POST \
  --url https://apiany.ai/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-5.5",
  "input": "审核这个 API 设计并列出主要风险。",
  "reasoning": {
    "effort": "high",
    "summary": "auto"
  },
  "text": {
    "verbosity": "medium"
  }
}
'
{
  "id": "<string>",
  "object": "response",
  "status": "<string>",
  "model": "<string>",
  "output": [
    {}
  ],
  "created_at": 123,
  "output_text": "<string>",
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123,
    "input_tokens": 123,
    "output_tokens": 123,
    "cached_input_tokens": 123
  }
}

Autorisations

​
Authorization
string
header
requis

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Corps

application/json
​
model
string
requis
Exemple:

"gpt-5.5"

​
input
requis

Input Responses. Peut être une chaîne de caractères ou un tableau d'items message / tool-result.

​
instructions
string

Instructions système ou développeur.

​
max_output_tokens
integer

Nombre maximal de tokens de sortie.

Plage requise: x >= 1
​
temperature
number
Plage requise: 0 <= x <= 2
​
top_p
number
Plage requise: 0 <= x <= 1
​
reasoning
object
​
text
object
​
tools
object[]

Outils Responses, incluant les function tools et les outils intégrés tels que web_search_preview.

​
tool_choice
​
stream
boolean

Si true, renvoie des événements SSE OpenAI Responses.

​
metadata
object

Réponse

OpenAI-compatible Responses response.

​
id
string
requis
​
object
string
requis
Exemple:

"response"

​
status
string
requis
​
model
string
requis
​
output
object[]
requis
​
created_at
integer
​
output_text
string
​
usage
object