Docs menu

Docs / API

Responses

POST /v1/responses in the OpenAI Responses format.

Last updated


Your setup

Fills in YOUR_API_KEY in the code on this page. The key stays in this tab: it is never sent and never saved.

Endpoint

POST https://api.cent-ai.dev/v1/responses
Authorization: Bearer cai_<secret>
Content-Type: application/json

The endpoint follows the OpenAI Responses format. Use the base URL https://api.cent-ai.dev/v1.

Request

model, input, stream, tools, reasoning and previous_response_id are sent to the model as is, like every other parameter.

TopicBehaviour
previous_response_idPassed through unchanged
storePassed to the model when it supports it. Cent AI does not keep response state itself
Usageusage.input_tokens, usage.input_tokens_details.cached_tokens and usage.output_tokens, plus usage.cost

Example

curl https://api.cent-ai.dev/v1/responses \
  -H "Authorization: Bearer $CENT_AI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-6-sol","input":"Hello"}'

Response

{
  "id": "resp_7a1",
  "object": "response",
  "model": "gpt-6-sol",
  "status": "completed",
  "output": [{"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": "Hello!"}]}],
  "usage": {
    "input_tokens": 5200,
    "input_tokens_details": {"cached_tokens": 4800},
    "output_tokens": 310,
    "total_tokens": 5510,
    "cost": "0.000124000"
  }
}

Streaming

With stream: true you receive the standard Responses events: response.created, response.output_text.delta and response.completed. The response object inside response.completed carries usage.cost. If the stream fails after it started, you receive response.failed with the error code, see Stream timeout.

event: response.created
data: {"type":"response.created","sequence_number":0,"response":{"id":"resp_7a1","object":"response","created_at":1792051200,"status":"in_progress","model":"gpt-6-sol","output":[],"usage":null}}

event: response.output_text.delta
data: {"type":"response.output_text.delta","sequence_number":4,"item_id":"msg_7a1","output_index":0,"content_index":0,"delta":"Hello","logprobs":[]}

event: response.completed
data: {"type":"response.completed","sequence_number":7,"response":{"id":"resp_7a1","object":"response","created_at":1792051200,"status":"completed","model":"gpt-6-sol","output":[{"type":"message","id":"msg_7a1","role":"assistant","status":"completed","content":[{"type":"output_text","text":"Hello!","annotations":[]}]}],"usage":{"input_tokens":5200,"input_tokens_details":{"cached_tokens":4800},"output_tokens":310,"total_tokens":5510,"cost":"0.000124000"}}}

The example is shortened: other standard events, such as response.output_item.added and response.content_part.added, arrive between these and are passed on too.

Contract


POST/v1/responses

Responses (OpenAI format)

Auth · API key (Bearer or x-api-key)

Request body

  • inputobjectrequired

  • modelstringrequired

  • previous_response_idstringoptional

  • storebooleanoptional

  • streambooleanoptional

Responses

  • 200Response object, or an SSE stream of Responses events; usage.cost is on the response in response.completed.
  • 400Error in the OpenAI shape.
  • 401Error in the OpenAI shape.
  • 402Error in the OpenAI shape.
  • 403Error in the OpenAI shape.
  • 404Error in the OpenAI shape.
  • 413Error in the OpenAI shape.
  • 429Error in the OpenAI shape that may be retried after Retry-After.retry
  • 500Error in the OpenAI shape.
  • 503Error in the OpenAI shape that may be retried after Retry-After.retry

Response headers

Retry-Afterx-request-id

Generated from the OpenAPI contract.