Skip to main content
POST
/
v3
/
compat
/
responses
Responses API
curl --request POST \
  --url https://api.opper.ai/v3/compat/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{}'
{
  "created_at": 123,
  "error": {
    "code": "<string>",
    "message": "<string>"
  },
  "id": "<string>",
  "incomplete_details": "<unknown>",
  "model": "<string>",
  "object": "<string>",
  "output": [
    {
      "type": "<string>",
      "arguments": "<string>",
      "call_id": "<string>",
      "content": [
        {
          "type": "<string>",
          "annotations": [
            "<unknown>"
          ],
          "text": "<string>"
        }
      ],
      "id": "<string>",
      "name": "<string>",
      "role": "<string>",
      "status": "<string>"
    }
  ],
  "status": "<string>",
  "tool_choice": "<unknown>",
  "cost": 123,
  "instructions": "<string>",
  "max_output_tokens": 123,
  "metadata": {},
  "output_text": "<string>",
  "previous_response_id": "<string>",
  "reasoning": {
    "effort": "<string>",
    "summary": "<string>"
  },
  "temperature": 123,
  "tools": [
    {
      "type": "<string>",
      "description": "<string>",
      "headers": {},
      "name": "<string>",
      "parameters": {},
      "require_approval": "<string>",
      "server_label": "<string>",
      "server_url": "<string>"
    }
  ],
  "top_p": 123,
  "usage": {
    "input_tokens": 123,
    "output_tokens": 123,
    "total_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens_details": {
      "reasoning_tokens": 123
    }
  },
  "user": "<string>"
}

Authorizations

​
Authorization
string
header
required

API key authentication. Pass your API key as a Bearer token.

Headers

​
X-Opper-Name
string

Function name for tracing and routing.

​
X-Opper-Parent-Span-Id
string<uuid>

Parent span ID for distributed tracing context.

​
X-Opper-Guard-Input
string

Comma-separated input guardrail checks (e.g. "pii,secrets").

​
X-Opper-Guard-Output
string

Comma-separated output guardrail checks (e.g. "toxicity").

​
X-Opper-Guard-Action
enum<string>
default:flag

Action for guardrail violations: "flag" (default), "block", or "redact".

Available options:
flag,
block,
redact

Body

application/json
​
input
object
​
instructions
string
​
max_output_tokens
integer
​
metadata
object
​
model
string
​
previous_response_id
string
​
reasoning
object
​
store
boolean
​
stream
boolean
​
temperature
number
​
text
object
​
tool_choice
any

Any value

​
tools
object[]
​
top_p
number
​
user
string

Response

Successful response

​
created_at
number
required
​
error
object
required
​
id
string
required
​
incomplete_details
any
required

Any value

​
model
string
required
​
object
string
required
​
output
object[]
required
​
status
string
required
​
tool_choice
any
required

Any value

​
cost
number
​
instructions
string
​
max_output_tokens
integer
​
metadata
object
​
output_text
string
​
previous_response_id
string
​
reasoning
object
​
temperature
number
​
tools
object[]
​
top_p
number
​
usage
object
​
user
string