Skip to main content
POST
/
v1
/
responses
curl --request POST \ --url https://api.caprioletech.com/v1/responses \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data ' { "model": "openai/gpt-5.5", "input": "Hello World!" } '
{}

Documentation Index

Fetch the complete documentation index at: https://docs.capriole.ai/llms.txt

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

Use this endpoint when your application, SDK, or agent expects the OpenAI Responses request and response format. Send a standard Responses payload with model and input. Capriole AI rewrites the model value to the selected upstream model ID, forwards compatible fields such as instructions, tools, reasoning, previous_response_id, and stream, and returns the upstream JSON or SSE stream unchanged. For simple Capriole-native text generation, use POST /v1/chat. Use POST /v1/responses when OpenAI Responses wire behavior is required.

Authorizations

​
Authorization
string
header
required

Use an API key created in the Capriole AI page. Send it as Authorization: Bearer sk-....

Body

application/json
​
model
enum<string>
required

Public OpenAI Responses model identifier

Available options:
openai/gpt-5.5,
openai/gpt-5.4-mini
​
input
required

OpenAI Responses input string or item list.

​
instructions
string

Optional system-level instructions.

​
tools
object[]

OpenAI Responses-compatible tool definitions.

​
reasoning
object

OpenAI Responses-compatible reasoning options.

​
stream
boolean
default:false

Stream the response as OpenAI Responses-compatible server-sent events.

Response

OpenAI Responses-compatible JSON response or SSE stream

OpenAI Responses-compatible response body.